© 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. 23-RESID-POST-AA
    6. 105100
    Prev
    Next
    INDEX
    Explanations

    with or had

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     directive
    -0.07
     deductible
    -0.07
     Brew
    -0.06
     Taipei
    -0.06
     remake
    -0.06
     Brian
    -0.06
    ительного
    -0.06
    Sure
    -0.06
     regulations
    -0.06
     *@
    -0.06
    POSITIVE LOGITS
    _plus
    0.06
     MSE
    0.06
    <!--[
    0.06
    _HERE
    0.06
     notas
    0.06
    .NoSuch
    0.06
     spielen
    0.06
    _platform
    0.06
     StringIO
    0.06
    CFG
    0.06
    Activations Density 0.040%

    No Known Activations