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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21193
    Prev
    Next
    INDEX
    Explanations

    hydrophobicity

    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
    oooooooo
    -0.07
     zu
    -0.07
     loud
    -0.06
    .richTextBox
    -0.06
    .after
    -0.06
    ès
    -0.06
    존
    -0.06
    	J
    -0.06
     ANSI
    -0.06
     potrav
    -0.06
    POSITIVE LOGITS
    الع
    0.07
     dissatisfaction
    0.06
    �
    0.06
     suff
    0.06
     QE
    0.06
    employment
    0.06
    Andrew
    0.06
     downloadable
    0.06
    sessions
    0.06
     Writers
    0.06
    Activations Density 0.008%

    No Known Activations