© 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. 6418
    Prev
    Next
    INDEX
    Explanations

    IS

    np_max-act · gemini-2.0-flash

    The neuron detects short all-caps two-letter strings (e.g. “IS,” “SM,” “QC”)—i.e. brief uppercase abbreviations.

    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
     Fo
    -0.07
    .Description
    -0.07
    มากกว
    -0.07
     pea
    -0.06
    ocre
    -0.06
     decreased
    -0.06
     гриб
    -0.06
    lasting
    -0.06
     buflen
    -0.06
     multip
    -0.06
    POSITIVE LOGITS
    .act
    0.07
    833
    0.06
     チ
    0.06
    xmin
    0.06
    주소
    0.06
    反
    0.06
    gens
    0.06
     shocks
    0.06
    goal
    0.06
     elektron
    0.06
    Activations Density 0.000%

    No Known Activations