© 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. 7-RESID-POST-AA
    11. 91344
    Prev
    Next
    INDEX
    Explanations

    uniform

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _started
    -0.07
     وأ
    -0.07
     exited
    -0.07
    .back
    -0.07
     goodbye
    -0.06
    let
    -0.06
    가는
    -0.06
    [Z
    -0.06
     подраз
    -0.06
     çöz
    -0.06
    POSITIVE LOGITS
     uniform
    0.17
     Uniform
    0.16
    Uniform
    0.12
    uniform
    0.12
    _uniform
    0.11
     uniformly
    0.11
     uniforms
    0.11
    iform
    0.10
    _UNIFORM
    0.08
     glUniform
    0.08
    Activations Density 0.004%

    No Known Activations