© 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. 109761
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects procedural‐instruction verbs (e.g. “omit,” “need to …”) and their immediate objects in instructional or how‐to contexts.

    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
    Ascending
    -0.07
    τον
    -0.07
    -cigaret
    -0.07
     bất
    -0.06
     tor
    -0.06
     Hayward
    -0.06
    альный
    -0.06
     Eid
    -0.06
    verting
    -0.06
     Meh
    -0.06
    POSITIVE LOGITS
    .Hash
    0.08
     lãnh
    0.07
    _xpath
    0.06
     FBI
    0.06
    .sqrt
    0.06
     repmat
    0.06
    ilitary
    0.06
     Security
    0.06
    .matrix
    0.06
    =user
    0.06
    Activations Density 0.115%

    No Known Activations