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. 50799
    Prev
    Next
    INDEX
    Explanations

    spectroscopy

    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
     Además
    -0.07
     Procedures
    -0.06
    Comput
    -0.06
    _COMP
    -0.06
     favourable
    -0.06
    ato
    -0.06
    _CI
    -0.06
     spouses
    -0.06
     лікування
    -0.06
     procedures
    -0.06
    POSITIVE LOGITS
    .Sockets
    0.06
    descr
    0.06
     Opp
    0.06
    mq
    0.06
     MatDialog
    0.06
     فرود
    0.06
    _Error
    0.06
     Nem
    0.06
     rivers
    0.06
    r
    0.06
    Activations Density 0.007%

    No Known Activations