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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 104040
    Prev
    Next
    INDEX
    Explanations

    ox

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sharon
    -0.07
     Half
    -0.07
    defense
    -0.07
    _draw
    -0.07
    .XtraGrid
    -0.07
    ी)
    -0.07
     Steam
    -0.06
    зь
    -0.06
    Intro
    -0.06
     Před
    -0.06
    POSITIVE LOGITS
    problems
    0.06
     authoritative
    0.06
     redefine
    0.06
    -placement
    0.06
     authorities
    0.06
    ué
    0.06
     Lust
    0.05
     }));↵
    0.05
    ()?.
    0.05
     repayment
    0.05
    Activations Density 0.008%

    No Known Activations