© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 127157
    Prev
    Next
    INDEX
    Explanations

    for to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lack
    -0.06
    ハ
    -0.06
    erequisite
    -0.06
     carry
    -0.06
     going
    -0.06
     addressing
    -0.06
    .="<
    -0.06
     apply
    -0.06
    aa
    -0.06
     feel
    -0.06
    POSITIVE LOGITS
    "?↵↵
    0.07
    idal
    0.07
    Выб
    0.07
     слыш
    0.07
    numerusform
    0.06
     skirm
    0.06
    RowAtIndexPath
    0.06
    Vect
    0.06
     coli
    0.06
     глиб
    0.06
    Activations Density 0.019%

    No Known Activations