© 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. 110269
    Prev
    Next
    INDEX
    Explanations

    empty

    np_max-act · gemini-2.0-flash

    This neuron fires on technical qualifier adjectives in mathematical statements (e.g. “non-empty,” “finite,” “bounded,” “compact,” “open,” etc.).

    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
     ویرایش
    -0.07
    神
    -0.06
     disgrace
    -0.06
    เทคโนโลย
    -0.06
    ичних
    -0.06
    .spatial
    -0.06
     UnsupportedOperationException
    -0.06
     Modular
    -0.06
     リ
    -0.06
     ************************************************
    -0.06
    POSITIVE LOGITS
     Cumhuriyeti
    0.08
    �
    0.07
    bserv
    0.07
    _boot
    0.07
    }$
    0.07
    summ
    0.07
     vin
    0.06
     vuel
    0.06
     ар
    0.06
    oriously
    0.06
    Activations Density 0.006%

    No Known Activations