© 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. 91597
    Prev
    Next
    INDEX
    Explanations

    communication

    np_max-act · gemini-2.0-flash

    This neuron activates on listing of required skills, qualifications, or numeric experience requirements in job-description bullet points.

    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
    /apis
    -0.07
     Two
    -0.06
    ***↵
    -0.06
    Ar
    -0.06
    datos
    -0.06
     reels
    -0.06
    authenticate
    -0.06
     concurrency
    -0.06
    Postal
    -0.06
    атар
    -0.06
    POSITIVE LOGITS
    stitution
    0.07
    ­i
    0.07
    -generic
    0.07
     сост
    0.06
     constitution
    0.06
     modific
    0.06
    irst
    0.06
    /photo
    0.06
    _ph
    0.06
    ,),
    0.06
    Activations Density 0.031%

    No Known Activations