© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44220
    Prev
    Next
    INDEX
    Explanations

    legal suppression/termination

    np_max-act · gemini-2.0-flash

    The neuron activates on noun tokens ending in “-tion” (e.g. suppression, termination, adoption)—that is, legal procedural terms formed with the “-tion” suffix.

    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
     LV
    -0.06
     xl
    -0.06
    zeigen
    -0.06
    alarını
    -0.05
     Griffith
    -0.05
    _ENT
    -0.05
    ImageRelation
    -0.05
     contender
    -0.05
     filings
    -0.05
     Gate
    -0.05
    POSITIVE LOGITS
    ومی
    0.07
     peasant
    0.07
    wechat
    0.07
     stupid
    0.07
    award
    0.06
    ORED
    0.06
     VLAN
    0.06
    -dismiss
    0.06
    $page
    0.06
     resistor
    0.06
    Activations Density 0.012%

    No Known Activations