© 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. 7-RESID-POST-AA
    11. 128116
    Prev
    Next
    INDEX
    Explanations

    the

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ionale
    -0.07
    Reality
    -0.07
    ionales
    -0.07
     Ro
    -0.06
    erti
    -0.06
    SION
    -0.06
    mani
    -0.06
     startups
    -0.06
    PET
    -0.06
    clared
    -0.06
    POSITIVE LOGITS
     بال
    0.07
    	Read
    0.06
    こん
    0.06
    '%(
    0.06
    "H
    0.06
     PropTypes
    0.06
    (full
    0.06
    ुह
    0.06
     Back
    0.06
     لل
    0.06
    Activations Density 0.056%

    No Known Activations