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. 7201
    Prev
    Next
    INDEX
    Explanations

    199

    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
    Incoming
    -0.07
    reland
    -0.07
    .related
    -0.07
     podí
    -0.07
     Crest
    -0.06
     Abel
    -0.06
    San
    -0.06
    Numbers
    -0.06
    pton
    -0.06
     diaper
    -0.06
    POSITIVE LOGITS
     searchData
    0.06
     उनक
    0.06
     MISSING
    0.06
    $is
    0.05
    .Operator
    0.05
     donner
    0.05
     had
    0.05
     půl
    0.05
    ॉय
    0.05
     UART
    0.05
    Activations Density 0.004%

    No Known Activations