© 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. 834
    Prev
    Next
    INDEX
    Explanations

    oh

    np_max-act · gemini-2.0-flash

    This neuron detects dynamic action verbs, especially those describing motion or other concrete actions (e.g., opened, walking, jumped).

    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
     beach
    -0.07
     느�
    -0.07
     Howe
    -0.07
     blade
    -0.06
    $url
    -0.06
    ельзя
    -0.06
    stat
    -0.06
    quant
    -0.06
     dělat
    -0.06
    -making
    -0.06
    POSITIVE LOGITS
    (savedInstanceState
    0.07
     veya
    0.06
    .Settings
    0.06
     »↵
    0.06
    ứng
    0.06
    _typeof
    0.06
    ницип
    0.06
    .REG
    0.06
    redirectToRoute
    0.06
     대표
    0.06
    Activations Density 0.002%

    No Known Activations