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. 100833
    Prev
    Next
    INDEX
    Explanations

    open parenthesis single quote

    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
    -generated
    -0.06
    row
    -0.06
    _timeline
    -0.06
    ,’’
    -0.06
    .AddSingleton
    -0.06
     ministers
    -0.06
    Putin
    -0.06
    Saturday
    -0.06
    -colored
    -0.06
    _identity
    -0.05
    POSITIVE LOGITS
     Mock
    0.08
    @param
    0.07
    Tuple
    0.07
     Quint
    0.06
     Delicious
    0.06
     Львів
    0.06
     Here
    0.06
    /*↵
    0.06
     Ζ
    0.06
     kullanıl
    0.06
    Activations Density 0.001%

    No Known Activations