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. 19-RESID-POST-AA
    6. 111931
    Prev
    Next
    INDEX
    Explanations

    offers resources allowing

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supplementation
    -0.06
     들
    -0.06
     »↵
    -0.06
     kidnapping
    -0.06
     regrets
    -0.06
    langs
    -0.06
    ‌تر
    -0.06
     форме
    -0.06
     custody
    -0.05
    あげ
    -0.05
    POSITIVE LOGITS
    .w
    0.07
    OVER
    0.07
     Dutch
    0.06
     Xuân
    0.06
    ilibrium
    0.06
    	module
    0.06
    .SUB
    0.06
    _ret
    0.06
    WARD
    0.06
    Signed
    0.06
    Activations Density 0.349%

    No Known Activations