© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 848
    Prev
    Next
    INDEX
    Explanations

    adjectives in scientific texts

    np_max-act · gemini-2.0-flash

    The neuron fires on adjectives or adjective pairs that label contrasting states or conditions (e.g. active/passive, relative/absolute, mixed/blocked, complicated/uncomplicated, transient/persistent, automatic/focused, major/minor, immediate/non-immediate).

    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
     یک
    -0.07
     xd
    -0.07
     adul
    -0.07
    icolon
    -0.07
     остров
    -0.06
    reserve
    -0.06
    _about
    -0.06
    $$$
    -0.06
    morph
    -0.06
    still
    -0.06
    POSITIVE LOGITS
     FIRE
    0.06
     Bav
    0.06
    (figsize
    0.06
     yerleştir
    0.06
    .OrderBy
    0.06
    .cod
    0.06
     Searching
    0.06
    Nam
    0.06
    .Payload
    0.06
     RowBox
    0.06
    Activations Density 0.115%

    No Known Activations