© 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. 19-RESID-POST-AA
    11. 28114
    Prev
    Next
    INDEX
    Explanations

    Sports betting/scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perspective
    -0.06
    蛇
    -0.06
    sector
    -0.06
     Andy
    -0.06
    스터
    -0.06
     حر
    -0.06
     sạch
    -0.06
    .String
    -0.06
    (pwd
    -0.06
    世界
    -0.06
    POSITIVE LOGITS
    ("{\"
    0.06
    xFD
    0.06
    bia
    0.06
    rada
    0.06
     aumento
    0.06
    芸
    0.06
    .visitVarInsn
    0.06
    อ
    0.06
    _WORD
    0.06
    .pageSize
    0.06
    Activations Density 0.008%

    No Known Activations