© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47289
    Prev
    Next
    INDEX
    Explanations

    ital

    np_max-act · gemini-2.0-flash

    references to rocket technology and space exploration companies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of “orbital” (including in compounds like “suborbital”), i.e. mentions of suborbital or orbital space flights or launches.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kelly
    -0.07
     nella
    -0.07
     transformed
    -0.06
    Nearly
    -0.06
    Dao
    -0.06
    Sau
    -0.06
    _FRE
    -0.06
    .setLevel
    -0.06
     войны
    -0.06
    Ral
    -0.06
    POSITIVE LOGITS
    getMockBuilder
    0.07
    �
    0.07
    _Desc
    0.07
    čas
    0.07
     Portal
    0.06
     Assy
    0.06
     arp
    0.06
     뛰
    0.06
     Courier
    0.06
     Burnett
    0.06
    Activations Density 0.001%

    No Known Activations