© 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. 7-RESID-POST-AA
    11. 30599
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific abbreviations

    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_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
     adulti
    -0.07
     озна
    -0.06
    パン
    -0.06
     Giang
    -0.06
    were
    -0.06
     زي
    -0.06
    óng
    -0.06
     eğ
    -0.06
    .rpm
    -0.06
    ryption
    -0.06
    POSITIVE LOGITS
     aus
    0.06
     susceptibility
    0.06
    -download
    0.06
     Arbit
    0.06
     antlr
    0.06
     cms
    0.06
     purposely
    0.05
    ostringstream
    0.05
     esos
    0.05
    -BEGIN
    0.05
    Activations Density 0.111%

    No Known Activations