© 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. 73649
    Prev
    Next
    INDEX
    Explanations

    About words/slang

    np_max-act · gemini-2.0-flash

    This neuron detects references to language evolution or the introduction of new words (e.g. mentions of “evolving,” “new words,” “being added,” 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
    })();↵
    -0.06
    Evaluate
    -0.06
    entin
    -0.06
     convin
    -0.06
     cultivated
    -0.06
    vals
    -0.06
     nost
    -0.06
     richest
    -0.06
    abled
    -0.05
    (per
    -0.05
    POSITIVE LOGITS
    /DD
    0.08
    /u
    0.07
    _Style
    0.06
    じ
    0.06
    Layout
    0.06
    /L
    0.06
     TASK
    0.06
     quỹ
    0.06
     Drone
    0.06
     skewed
    0.06
    Activations Density 0.051%

    No Known Activations