Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 42460
    Prev
    Next
    INDEX
    Explanations

    user-generated text

    np_max-act · gemini-2.0-flash

    This neuron detects the modal verb “should,” i.e. spots normative/advisory phrasing.

    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
    รรค
    -0.07
     SL
    -0.06
     싶
    -0.06
    ニ
    -0.06
     ":
    -0.06
     femmes
    -0.06
     Ap
    -0.06
    �
    -0.06
    _was
    -0.06
     speci
    -0.06
    POSITIVE LOGITS
    .");
    ↵
    0.07
    .Status
    0.07
    cej
    0.07
    .TRUE
    0.06
     constit
    0.06
    _Format
    0.06
     Err
    0.06
    .An
    0.06
    [char
    0.06
     VECTOR
    0.06
    Activations Density 0.001%

    No Known Activations