© 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. 129650
    Prev
    Next
    INDEX
    Explanations

    key

    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
     stale
    -0.06
     للس
    -0.06
    learning
    -0.06
     后
    -0.06
     Sang
    -0.06
     slav
    -0.06
     температуры
    -0.06
     Params
    -0.06
     consumer
    -0.06
     writers
    -0.06
    POSITIVE LOGITS
    :mm
    0.07
    ์ว
    0.07
    _disable
    0.07
    eva
    0.06
    ois
    0.06
    ủi
    0.06
    Mich
    0.06
    ensation
    0.06
     dní
    0.06
    olly
    0.06
    Activations Density 0.000%

    No Known Activations