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. 7-RESID-POST-AA
    6. 93666
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mitch
    -0.07
     ค
    -0.06
     tř
    -0.06
    (configuration
    -0.06
    �
    -0.06
    prep
    -0.06
    Pipe
    -0.06
    ilee
    -0.06
    หว
    -0.06
     ierr
    -0.06
    POSITIVE LOGITS
     Sanct
    0.08
     христи
    0.07
     synerg
    0.06
     synth
    0.06
     Handbook
    0.06
    _help
    0.06
    _ATTRIB
    0.06
     Configuration
    0.06
     IRQ
    0.06
     acquire
    0.06
    Activations Density 0.035%

    No Known Activations