Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 9325
    Prev
    Next
    INDEX
    Explanations

    Code

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ุมชน
    -0.08
     CLASS
    -0.07
    	status
    -0.07
    _points
    -0.07
    simd
    -0.06
    ))*(
    -0.06
     ery
    -0.06
    )||
    -0.06
    _identity
    -0.06
    __))
    -0.06
    POSITIVE LOGITS
    GREEN
    0.06
    áhnout
    0.06
    ◎
    0.06
    ribly
    0.06
    слід
    0.06
    mir
    0.06
    ้ร
    0.06
     generar
    0.06
    abet
    0.06
    Tony
    0.06
    Activations Density 0.040%

    No Known Activations