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. 27-RESID-POST-AA
    6. 103512
    Prev
    Next
    INDEX
    Explanations

    German language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nouvelles
    -0.08
     defa
    -0.07
     Entries
    -0.07
    Three
    -0.07
    出了
    -0.07
     estimate
    -0.07
     vitae
    -0.07
     contracts
    -0.07
     Three
    -0.07
     skepticism
    -0.07
    POSITIVE LOGITS
     Charlottesville
    0.07
    ckill
    0.07
    :pointer
    0.06
    _br
    0.06
    aleb
    0.06
     Joomla
    0.06
     antlr
    0.06
    _AA
    0.06
    ?option
    0.06
    "]]
    0.06
    Activations Density 0.071%

    No Known Activations