Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 129061
    Prev
    Next
    INDEX
    Explanations

    References and links

    np_max-act · gemini-2.0-flash

    This neuron activates on the names and titles of external reference or “External links” entries at the ends of articles.

    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
     chung
    -0.06
    liğine
    -0.06
     extinct
    -0.06
    �
    -0.06
    ocus
    -0.06
    emplate
    -0.06
    เกษ
    -0.06
    Attempting
    -0.06
    producer
    -0.06
    dir
    -0.06
    POSITIVE LOGITS
    _DIRS
    0.07
     {{--<
    0.07
     '}';↵
    0.07
     xbmc
    0.06
     canadian
    0.06
     Foley
    0.06
    ---------------↵
    0.06
    @Data
    0.06
     μικ
    0.06
     Bron
    0.06
    Activations Density 0.006%

    No Known Activations