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. 23-RESID-POST-AA
    6. 103829
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     která
    -0.07
    mass
    -0.06
    anges
    -0.06
    _neurons
    -0.06
    #pragma
    -0.06
     VALUES
    -0.06
    AGON
    -0.06
     Immutable
    -0.06
    prav
    -0.06
     resmi
    -0.06
    POSITIVE LOGITS
    btc
    0.07
    _FA
    0.07
    _RDONLY
    0.07
     mr
    0.07
     크
    0.06
    (strlen
    0.06
     privileges
    0.06
     contexts
    0.06
     NO
    0.06
    _aligned
    0.06
    Activations Density 0.004%

    No Known Activations