© 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. 23-RESID-POST-AA
    11. 7911
    Prev
    Next
    INDEX
    Explanations

    infancy

    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
    ’y
    -0.06
     layered
    -0.06
     prima
    -0.06
    ้ท
    -0.06
     bile
    -0.06
    &apos
    -0.06
     Jonathan
    -0.06
    Jonathan
    -0.06
    してい
    -0.06
     JV
    -0.06
    POSITIVE LOGITS
     inf
    0.08
    Inf
    0.08
    ورش
    0.08
    inf
    0.08
     Inf
    0.08
    жа
    0.07
    лом
    0.07
    amba
    0.07
     infos
    0.07
    eni
    0.07
    Activations Density 0.031%

    No Known Activations