© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89114
    Prev
    Next
    INDEX
    Explanations

    Possibility/capability

    np_max-act · gemini-2.0-flash

    references to additive fabrication technologies and their implications in various applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words expressing ability or possibility (modal/auxiliary terms like “possible,” “do,” “can,” “will,” 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
    .translatesAutoresizingMaskIntoConstraints
    -0.07
    /S
    -0.07
     amassed
    -0.06
    /r
    -0.06
     loop
    -0.06
    nds
    -0.06
     bey
    -0.06
    defense
    -0.06
    hasMany
    -0.06
     equally
    -0.06
    POSITIVE LOGITS
    punkt
    0.07
     organizing
    0.07
    给
    0.06
     громадян
    0.06
     futile
    0.06
     администра
    0.06
    masına
    0.06
     lawmakers
    0.06
    .WindowManager
    0.06
     tail
    0.06
    Activations Density 0.027%

    No Known Activations