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. 11-RESID-POST-AA
    6. 77466
    Prev
    Next
    INDEX
    Explanations

    Name origins and meanings

    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
     occurs
    -0.07
     occur
    -0.07
     dictated
    -0.06
     attended
    -0.06
    pekt
    -0.06
    	Test
    -0.06
    Assets
    -0.06
    獎
    -0.06
    standing
    -0.06
    kle
    -0.06
    POSITIVE LOGITS
    ANNOT
    0.07
    สถ
    0.07
     naken
    0.06
    647
    0.06
    empor
    0.06
     belg
    0.06
    \ActiveForm
    0.06
     dönemde
    0.06
     kent
    0.06
     мяг
    0.06
    Activations Density 0.065%

    No Known Activations