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. 105528
    Prev
    Next
    INDEX
    Explanations

    plotting code/data

    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
    commend
    -0.07
    iton
    -0.07
    _override
    -0.07
    Comparator
    -0.06
    Issuer
    -0.06
    <Component
    -0.06
     Định
    -0.06
    905
    -0.06
    mnop
    -0.06
     foe
    -0.06
    POSITIVE LOGITS
    حة
    0.07
     TypeError
    0.06
    ]];↵↵
    0.06
     YÖ
    0.06
     Independent
    0.06
    (admin
    0.06
    ()
    ↵
    ↵
    ↵
    0.06
    ());
    ↵
    ↵
    0.06
    	   ↵
    0.06
    omnia
    0.06
    Activations Density 0.004%

    No Known Activations