© 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. 15-RESID-POST-AA
    11. 11932
    Prev
    Next
    INDEX
    Explanations

    freezing and thawing

    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
     Semester
    -0.07
     pure
    -0.07
     seek
    -0.07
    _cls
    -0.06
    kok
    -0.06
     horas
    -0.06
     Courses
    -0.06
    _session
    -0.06
     minute
    -0.06
     threads
    -0.06
    POSITIVE LOGITS
     Retrieves
    0.07
    �始
    0.06
     chiế
    0.06
    toBeInTheDocument
    0.06
    ladesh
    0.06
     transit
    0.06
     poss
    0.06
     　　　　　　　　　　　　　　　　
    0.06
    PR
    0.06
     협
    0.06
    Activations Density 0.218%

    No Known Activations