© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 75547
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    phrases that express quantity or magnitude, highlighting counts, amounts, and the significance or extent of something.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    lediği
    -0.07
     Agility
    -0.06
     OSI
    -0.06
     جو
    -0.06
     арх
    -0.06
    <th
    -0.06
     techno
    -0.06
    .sf
    -0.06
    .Desc
    -0.06
    ,idx
    -0.06
    POSITIVE LOGITS
     puts
    0.08
    *this
    0.07
     избав
    0.07
    _option
    0.07
    Hat
    0.06
    =\"$
    0.06
     pass
    0.06
    istani
    0.06
     побед
    0.06
     come
    0.06
    Activations Density 0.377%

    No Known Activations