© 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. 23-RESID-POST-AA
    11. 105052
    Prev
    Next
    INDEX
    Explanations

    Code snippets and documentation

    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
    로는
    -0.06
    _updates
    -0.06
    άλυ
    -0.06
    _quit
    -0.06
    	en
    -0.06
     prerequisite
    -0.06
    OE
    -0.06
    Either
    -0.06
     mystery
    -0.06
    ै
    -0.06
    POSITIVE LOGITS
    /values
    0.07
    }$
    0.06
     паци
    0.06
    977
    0.06
    management
    0.06
    _coeffs
    0.06
     ****************************************
    0.06
     evalu
    0.06
     scri
    0.06
    ецт
    0.06
    Activations Density 0.000%

    No Known Activations