© 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 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. 11-RESID-POST-AA
    11. 37990
    Prev
    Next
    INDEX
    Explanations

    Biographical influences/work

    np_max-act · gemini-2.0-flash

    This neuron lights up on mentions of a person’s own creative works or output (e.g., songs, writings, influences, album, work).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    _array
    -0.06
     Vac
    -0.06
     satire
    -0.06
     tendencies
    -0.06
    weekly
    -0.06
     japan
    -0.06
    .SetFloat
    -0.06
    егор
    -0.06
    理由
    -0.06
    آمد
    -0.05
    POSITIVE LOGITS
    Й
    0.07
    VMLINUX
    0.07
    xFFFFFF
    0.07
    lbrace
    0.07
    (TR
    0.06
     Azure
    0.06
     Markup
    0.06
    _ids
    0.06
     distinctions
    0.06
     GLES
    0.06
    Activations Density 0.047%

    No Known Activations