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. 104715
    Prev
    Next
    INDEX
    Explanations

    say "heart" ending

    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
     easiest
    -0.06
     "=
    -0.06
     Modelo
    -0.06
     시스템
    -0.06
     Lists
    -0.06
    ером
    -0.06
    -reviewed
    -0.06
    .first
    -0.06
     Dict
    -0.06
    claration
    -0.06
    POSITIVE LOGITS
    .getSelection
    0.07
     scav
    0.06
     ώρα
    0.06
    .uni
    0.06
     Ü
    0.06
    .forName
    0.06
    .histogram
    0.06
    sendMessage
    0.06
     XD
    0.06
    Sortable
    0.06
    Activations Density 0.002%

    No Known Activations