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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 21431
    Prev
    Next
    INDEX
    Explanations

    those

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arin
    -0.07
    _parts
    -0.07
    된
    -0.07
    üstü
    -0.06
    RG
    -0.06
    artin
    -0.06
    ARC
    -0.06
    西省
    -0.06
     sea
    -0.06
     multipart
    -0.06
    POSITIVE LOGITS
     those
    0.13
    Those
    0.12
     Those
    0.11
    those
    0.11
    loyment
    0.07
     Institutes
    0.07
    Const
    0.07
     assigned
    0.07
    	     
    0.07
     Journalism
    0.07
    Activations Density 0.030%

    No Known Activations