© 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. 126086
    Prev
    Next
    INDEX
    Explanations

    Travel

    np_max-act · gemini-2.0-flash

    The neuron fires on proper names and other capitalized entities (like titles, brands, and place or model names).

    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
    _prog
    -0.07
    _gallery
    -0.07
    áng
    -0.07
    _mid
    -0.06
    .View
    -0.06
    FTP
    -0.06
    Paren
    -0.06
     spaces
    -0.06
     Auditor
    -0.06
     Highway
    -0.06
    POSITIVE LOGITS
     ασ
    0.06
     yöntem
    0.06
    ?>
    ↵
    0.06
    mdb
    0.06
     removeObject
    0.06
     společnost
    0.05
    exao
    0.05
    �断
    0.05
    upyter
    0.05
     prostate
    0.05
    Activations Density 0.104%

    No Known Activations