© 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. 3-RESID-POST-AA
    11. 94156
    Prev
    Next
    INDEX
    Explanations

    thaw

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presenta
    -0.07
     Neuro
    -0.06
     hardcore
    -0.06
    dance
    -0.06
    enk
    -0.06
     judged
    -0.06
    ategories
    -0.06
     Kramer
    -0.06
    ('=
    -0.06
     دیگران
    -0.06
    POSITIVE LOGITS
     thaw
    0.23
     challenging
    0.07
    aw
    0.07
    ectomy
    0.07
     Technician
    0.07
    duct
    0.06
    imestone
    0.06
    Deserialize
    0.06
    .setMaximum
    0.06
     Projects
    0.06
    Activations Density 0.002%

    No Known Activations