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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6919
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are parts of people’s names (e.g. first names, initials, and surnames) in legal filings.

    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
    яться
    -0.06
     火
    -0.06
    ระเบ
    -0.06
    のに
    -0.06
     harassing
    -0.06
    ために
    -0.06
    LayoutManager
    -0.06
    _BITS
    -0.05
    のだろう
    -0.05
    channel
    -0.05
    POSITIVE LOGITS
    _nom
    0.07
     lasc
    0.07
     Brett
    0.07
     Powell
    0.07
    .Round
    0.07
    -slider
    0.06
    bedo
    0.06
    -le
    0.06
     Lund
    0.06
     studi
    0.06
    Activations Density 0.023%

    No Known Activations