© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 35661
    Prev
    Next
    INDEX
    Explanations

    U

    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
    37
    -0.08
    Born
    -0.08
     جور
    -0.08
     Born
    -0.08
    -not
    -0.07
     Boyle
    -0.07
    “For
    -0.07
    "Not
    -0.07
     pare
    -0.07
    stein
    -0.07
    POSITIVE LOGITS
     U
    0.22
    U
    0.17
     u
    0.15
    .U
    0.13
    -U
    0.12
    _U
    0.12
    (U
    0.11
    -u
    0.11
    [U
    0.11
    	U
    0.11
    Activations Density 0.061%

    No Known Activations