Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 11324
    Prev
    Next
    INDEX
    Explanations

    Naming in problem-solving

    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_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
     加
    -0.07
    RegularExpression
    -0.06
    andelier
    -0.06
    .returnValue
    -0.06
     through
    -0.06
     prog
    -0.06
     IW
    -0.06
    OperationException
    -0.06
    (Test
    -0.06
     Gh
    -0.06
    POSITIVE LOGITS
     serene
    0.07
    (socket
    0.07
    WiFi
    0.06
    áři
    0.06
    _AMOUNT
    0.06
    _VOICE
    0.06
    ++)
    ↵
    0.06
    -white
    0.06
     bị
    0.06
     origin
    0.06
    Activations Density 0.033%

    No Known Activations