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. 36337
    Prev
    Next
    INDEX
    Explanations

    error

    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
     kariy
    -0.08
    ixe
    -0.07
    _Store
    -0.07
     アル
    -0.07
    Positive
    -0.06
     antibodies
    -0.06
    Salir
    -0.06
    basename
    -0.06
     alliance
    -0.06
     kosten
    -0.06
    POSITIVE LOGITS
     ['./
    0.06
    _Checked
    0.06
    +":
    0.06
     Å
    0.06
     ®
    0.06
    ision
    0.06
     interrupt
    0.06
     psy
    0.06
    ọi
    0.06
    \CMS
    0.06
    Activations Density 0.016%

    No Known Activations