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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117011
    Prev
    Next
    INDEX
    Explanations

    endotoxin

    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
    FixedSize
    -0.07
     ге
    -0.07
    essions
    -0.07
     sais
    -0.06
     follic
    -0.06
     galer
    -0.06
    -economic
    -0.06
    _REGEX
    -0.06
    .decor
    -0.06
    liğ
    -0.06
    POSITIVE LOGITS
     By
    0.06
    iams
    0.06
    ográf
    0.06
     Remove
    0.06
    terror
    0.06
    lain
    0.06
     acknowledges
    0.06
     discour
    0.06
     다음과
    0.06
    thanks
    0.06
    Activations Density 0.001%

    No Known Activations