© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 75858
    Prev
    Next
    INDEX
    Explanations

    avored

    np_max-act · gemini-2.0-flash

    sentences or boilerplate stating that citation of unpublished dispositions (per the Sixth Circuit rule) is disfavored.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    诗
    -0.06
    lost
    -0.06
     borr
    -0.06
    書
    -0.06
     lij
    -0.06
    _GENERIC
    -0.06
    (ps
    -0.06
    yyy
    -0.06
     submission
    -0.06
    ])
    ↵
    -0.05
    POSITIVE LOGITS
     anglais
    0.08
    .valueOf
    0.08
     erectile
    0.07
     καθώς
    0.07
    cular
    0.07
    ryfall
    0.07
    оруж
    0.06
    _gain
    0.06
    -view
    0.06
     Viewing
    0.06
    Activations Density 0.001%

    No Known Activations