© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 75104
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
     commas
    -0.07
     τα
    -0.07
    оба
    -0.07
    Ral
    -0.06
     expire
    -0.06
     Eg
    -0.06
     Christoph
    -0.06
     dracon
    -0.06
     configs
    -0.06
    npm
    -0.06
    POSITIVE LOGITS
     TestUtils
    0.07
    şehir
    0.06
    ehler
    0.06
    殖
    0.06
     UIBar
    0.06
    _hyper
    0.06
     üz
    0.06
    obbled
    0.06
    _cube
    0.06
    Beauty
    0.06
    Activations Density 0.136%

    No Known Activations