© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 59205
    Prev
    Next
    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash

    The neuron detects second‐person instructional phrasing—especially “you” and its accompanying modal/helping words (can, will, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     punishable
    -0.07
     Tau
    -0.07
    _pairs
    -0.07
    lbs
    -0.06
    _Map
    -0.06
    ず
    -0.06
     arresting
    -0.06
    .bz
    -0.06
    \b
    -0.06
    (indices
    -0.06
    POSITIVE LOGITS
    			↵			↵
    0.06
     earm
    0.06
    Hi
    0.06
    								↵
    0.06
     expectedResult
    0.06
    flo
    0.06
            ↵↵
    0.06
    TEGR
    0.06
     gente
    0.06
        ↵↵
    0.06
    Activations Density 0.025%

    No Known Activations