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. 41754
    Prev
    Next
    INDEX
    Explanations

    the

    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
     '".
    -0.07
    ・・
    -0.06
    }".
    -0.06
    passed
    -0.06
    =status
    -0.06
     sacrifice
    -0.06
    до
    -0.06
    -training
    -0.06
    ADV
    -0.06
     brushed
    -0.06
    POSITIVE LOGITS
    Dyn
    0.07
    му
    0.06
     Presidents
    0.06
     země
    0.06
     chaud
    0.06
    (pid
    0.06
     fed
    0.06
     คณะ
    0.06
    (cancel
    0.06
     Machinery
    0.06
    Activations Density 0.000%

    No Known Activations