© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 21025
    Prev
    Next
    INDEX
    Explanations

    ad

    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
    ##_
    -0.07
    	account
    -0.07
     şarkı
    -0.07
    chg
    -0.06
    —↵↵
    -0.06
     Blazers
    -0.06
    projection
    -0.06
     usuario
    -0.06
    _ATOM
    -0.06
     Lars
    -0.06
    POSITIVE LOGITS
     ihtiy
    0.07
     Mata
    0.07
    _tunnel
    0.06
    ी.
    0.06
     потріб
    0.06
     suggests
    0.06
    .toDouble
    0.06
    ationale
    0.06
     Barg
    0.06
     footage
    0.06
    Activations Density 0.000%

    No Known Activations