© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57509
    Prev
    Next
    INDEX
    Explanations

    Actions and hesitations

    np_max-act · gemini-2.0-flash

    The neuron fires on action words that denote a change of state or movement (e.g. switching, jumping into, buying, leaving).

    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
    ตลาด
    -0.07
     chơi
    -0.06
     outings
    -0.06
     Bankası
    -0.06
     Investigations
    -0.06
    放送
    -0.06
     뛰
    -0.06
    .";↵
    -0.06
    Advance
    -0.06
    elsen
    -0.06
    POSITIVE LOGITS
     recomm
    0.07
     immigrant
    0.07
    .SO
    0.07
     legit
    0.07
    .sum
    0.07
    なた
    0.06
    �
    0.06
    Utc
    0.06
    ucc
    0.06
     Wh
    0.06
    Activations Density 0.042%

    No Known Activations