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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 93182
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    uggestion
    -0.08
     grinding
    -0.07
    -click
    -0.07
    -fill
    -0.07
    इन
    -0.06
    ASON
    -0.06
    ='_
    -0.06
     Preparation
    -0.06
    allon
    -0.06
     hott
    -0.06
    POSITIVE LOGITS
     ++)
    0.07
    _PORTS
    0.06
    )data
    0.06
     res
    0.06
     wedge
    0.06
    _dst
    0.06
     уточ
    0.06
    dst
    0.06
     velik
    0.06
     EventArgs
    0.06
    Activations Density 0.010%

    No Known Activations