© 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. 51873
    Prev
    Next
    INDEX
    Explanations

    disclaiming prior art

    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_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
     gb
    -0.06
    Die
    -0.06
    zu
    -0.06
    _bad
    -0.06
    Pow
    -0.06
    avings
    -0.06
    $\
    -0.06
     ju
    -0.06
    Saving
    -0.06
     ub
    -0.06
    POSITIVE LOGITS
    .Basic
    0.08
    xpath
    0.07
     sx
    0.07
     suite
    0.06
     architectures
    0.06
     prospect
    0.06
    _RCC
    0.06
     *[
    0.06
    (route
    0.06
    ん
    0.06
    Activations Density 0.002%

    No Known Activations