© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 52155
    Prev
    Next
    INDEX
    Explanations

    2 or 3

    np_max-act · gemini-2.0-flash

    sentences that state whether a summary is factually consistent with a document (Yes/No evaluation).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .sys
    -0.07
    isl
    -0.07
     names
    -0.06
    anian
    -0.06
    ians
    -0.06
     glo
    -0.06
    .wp
    -0.06
    arded
    -0.06
    _import
    -0.06
    explo
    -0.06
    POSITIVE LOGITS
    lict
    0.07
    flake
    0.07
     　　　　　　　　　
    0.07
     ){
↵
    0.06
    filePath
    0.06
    ]){↵
    0.06
    _buff
    0.06
    .DIS
    0.06
     Discipline
    0.06
    ¶¶
    0.06
    Activations Density 0.006%

    No Known Activations