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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129773
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron fires on the “2.0” version string in the Apache license header.

    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
    .serv
    -0.06
    Tier
    -0.06
     Phot
    -0.06
    Indented
    -0.06
     terminal
    -0.06
     open
    -0.06
     OSP
    -0.06
    _ends
    -0.06
    (msg
    -0.06
     views
    -0.06
    POSITIVE LOGITS
    _Execute
    0.07
     şöyle
    0.07
     العربي
    0.07
     admittedly
    0.06
    ガ
    0.06
     recreation
    0.06
     Brazilian
    0.06
    共和国
    0.06
     fieldType
    0.06
     india
    0.06
    Activations Density 0.010%

    No Known Activations