Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 26085
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    Neuron 4 never responds to any token—it remains inactive and doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to coercive sexual situations and exploitation.

    oai_token-act-pair · gpt-4o-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
     normalization
    -0.07
    τού
    -0.07
     warranty
    -0.06
     Honestly
    -0.06
    _trace
    -0.06
    ožná
    -0.06
    τών
    -0.06
    тин
    -0.06
     Ment
    -0.06
    Allow
    -0.06
    POSITIVE LOGITS
     skb
    0.06
     كانت
    0.06
     छ
    0.06
    strip
    0.06
     serm
    0.06
     consul
    0.06
    +'
    0.06
    ักษ
    0.06
     opcode
    0.06
     ngOn
    0.06
    Activations Density 0.083%

    No Known Activations