© 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. 11-RESID-POST-AA
    11. 104857
    Prev
    Next
    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash

    phrases expressing hypotheticals, wishes, or modal/conditional requests (words like "would", "could", "wish" in hypothetical questions).

    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_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
    kte
    -0.07
    _SUPPORTED
    -0.07
    ReadStream
    -0.07
     系
    -0.06
     Я
    -0.06
    vable
    -0.06
    Af
    -0.06
    乾
    -0.06
     lobbyist
    -0.06
     Prosper
    -0.06
    POSITIVE LOGITS
    (sql
    0.07
    .Select
    0.07
     "'.
    0.07
     SQ
    0.07
     хотя
    0.07
    &type
    0.06
    amenti
    0.06
    _SECOND
    0.06
    air
    0.06
    -command
    0.06
    Activations Density 0.020%

    No Known Activations