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. 93180
    Prev
    Next
    INDEX
    Explanations

    glass

    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
    299
    -0.07
    bedo
    -0.07
    /">
    -0.07
     beled
    -0.07
    .DATE
    -0.06
     machinery
    -0.06
    131
    -0.06
     Notice
    -0.06
    .published
    -0.06
    iên
    -0.06
    POSITIVE LOGITS
     glass
    0.07
     kaybet
    0.07
    -bodied
    0.06
    ewear
    0.06
    �u
    0.06
     timber
    0.06
    ‌هاي
    0.06
    ीव
    0.06
    _Source
    0.06
    گاه
    0.06
    Activations Density 0.006%

    No Known Activations