© 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. 92072
    Prev
    Next
    INDEX
    Explanations

    magnetic

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of magnet-related terms (e.g., the substring “magnet”).

    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
     zřejmě
    -0.07
     кад
    -0.07
    .RunWith
    -0.07
    Center
    -0.06
     lille
    -0.06
    fare
    -0.06
    [vi
    -0.06
     пап
    -0.06
     APP
    -0.06
     많
    -0.06
    POSITIVE LOGITS
    اعة
    0.06
     concrete
    0.06
     decides
    0.06
    끔
    0.06
    building
    0.06
     turmoil
    0.06
    ورة
    0.06
    ,d
    0.06
     maxSize
    0.06
     rallies
    0.06
    Activations Density 0.004%

    No Known Activations