© 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. 7-RESID-POST-AA
    6. 113407
    Prev
    Next
    INDEX
    Explanations

    sh

    np_max-act · gemini-2.0-flash

    script-style roleplay lines with character name tags and parenthetical stage directions (dialogue labeled by a speaker followed by actions).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     güçlü
    -0.07
    ーニ
    -0.07
    sports
    -0.07
    NoSuch
    -0.07
    Played
    -0.06
    енности
    -0.06
    horn
    -0.06
     ngày
    -0.06
    比
    -0.06
     степ
    -0.06
    POSITIVE LOGITS
     Brig
    0.06
    gregation
    0.06
     Rolex
    0.06
     regist
    0.06
    ()}>↵
    0.06
    .est
    0.06
    entication
    0.06
    /cmd
    0.06
     functional
    0.05
    $search
    0.05
    Activations Density 0.039%

    No Known Activations