© 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. 68956
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on terms naming categories of disallowed or restricted content (e.g. sexual, violent, illegal, hateful, misleading) in moderation or censorship guidelines.

    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
    iscopal
    -0.07
     بای
    -0.06
    GetValue
    -0.06
     HttpURLConnection
    -0.06
    tolower
    -0.06
     imitation
    -0.06
    groupon
    -0.06
    ))));↵
    -0.06
    Postal
    -0.06
     transplant
    -0.06
    POSITIVE LOGITS
    _fonts
    0.07
     vra
    0.06
    드로
    0.06
     موجب
    0.06
    isch
    0.06
     český
    0.06
    قيق
    0.06
    ภ
    0.06
    fore
    0.06
     �
    0.06
    Activations Density 0.013%

    No Known Activations