© 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
    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. 75230
    Prev
    Next
    INDEX
    Explanations

    longitudinal

    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
    Beer
    -0.08
    _FA
    -0.07
     cram
    -0.07
     peanuts
    -0.06
    Ban
    -0.06
     네
    -0.06
    chemy
    -0.06
     Sanat
    -0.06
     rar
    -0.06
    .ac
    -0.06
    POSITIVE LOGITS
     longitudinal
    0.10
     longitud
    0.08
    seud
    0.07
    _offset
    0.07
    neh
    0.07
    وز
    0.07
    伤
    0.07
     prolong
    0.07
    ContentView
    0.07
    insi
    0.06
    Activations Density 0.004%

    No Known Activations