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. 27-RESID-POST-AA
    6. 60642
    Prev
    Next
    INDEX
    Explanations

    College

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discover
    -0.07
    ください
    -0.06
    Left
    -0.06
    Un
    -0.06
    Overflow
    -0.06
     gesch
    -0.06
    "C
    -0.06
    Minor
    -0.06
    (("
    -0.06
    _le
    -0.06
    POSITIVE LOGITS
    ])*
    0.06
    (requestCode
    0.06
     noodles
    0.06
    )localObject
    0.06
    sequently
    0.06
    itory
    0.06
     مختصات
    0.06
    (isolate
    0.06
     loginUser
    0.06
     يس
    0.06
    Activations Density 0.004%

    No Known Activations