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. 11-RESID-POST-AA
    6. 22232
    Prev
    Next
    INDEX
    Explanations

    ::

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INCLUDED
    -0.07
     прояв
    -0.06
     gravel
    -0.06
    ắng
    -0.06
    ]).
    -0.06
     xtype
    -0.06
    dana
    -0.06
     condu
    -0.06
    ná
    -0.06
    .learn
    -0.06
    POSITIVE LOGITS
     Sunshine
    0.06
     Toys
    0.06
    wives
    0.06
    /hr
    0.06
    ullet
    0.06
    .Sprintf
    0.06
     normals
    0.06
    _Stream
    0.06
     Dirty
    0.06
     Wis
    0.05
    Activations Density 0.003%

    No Known Activations