© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126762
    Prev
    Next
    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on in‐text citation markers and reference labels (e.g. bracketed “[@HS…]” tokens and author‐initial tags).

    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
     comm
    -0.07
    _inf
    -0.07
     Sawyer
    -0.06
     insured
    -0.06
     donation
    -0.06
    rust
    -0.06
     affidavit
    -0.06
    Replacing
    -0.06
     Raid
    -0.06
     vos
    -0.06
    POSITIVE LOGITS
     doğrult
    0.07
     허
    0.06
     Profes
    0.06
    dem
    0.06
     здійс
    0.06
     Değ
    0.06
     Vous
    0.06
     بم
    0.06
    าษฎ
    0.06
     Friendship
    0.06
    Activations Density 0.014%

    No Known Activations