© 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. 90732
    Prev
    Next
    INDEX
    Explanations

    outcome

    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
    ово
    -0.07
    iedo
    -0.07
     duty
    -0.06
     drainage
    -0.06
     "@/
    -0.06
    (sf
    -0.06
    -TV
    -0.06
     dap
    -0.06
    itical
    -0.06
    Cliente
    -0.06
    POSITIVE LOGITS
     relying
    0.07
     outcome
    0.07
     tímto
    0.07
     result
    0.07
    SAFE
    0.07
     loos
    0.07
     рав
    0.07
    ])]
    0.06
    _softmax
    0.06
     LJ
    0.06
    Activations Density 0.016%

    No Known Activations