© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 112172
    Prev
    Next
    INDEX
    Explanations

    of

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    La
    -0.08
     playoffs
    -0.07
    Ds
    -0.07
    Wy
    -0.07
    syscall
    -0.07
    hostname
    -0.07
    .Dataset
    -0.07
    bral
    -0.07
     OS
    -0.07
    _stats
    -0.07
    POSITIVE LOGITS
    (mysql
    0.06
     enumer
    0.06
     прин
    0.06
     have
    0.06
    _typeDefinitionSize
    0.05
    ยนตร
    0.05
     nightlife
    0.05
     subparagraph
    0.05
    ΑΤ
    0.05
    <File
    0.05
    Activations Density 0.036%

    No Known Activations