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. 15-RESID-POST-AA
    6. 53836
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    chia
    -0.08
     prompts
    -0.07
    _REF
    -0.07
    ном
    -0.06
     doping
    -0.06
     يق
    -0.06
     Cache
    -0.06
     розп
    -0.06
     цим
    -0.06
     parity
    -0.06
    POSITIVE LOGITS
    unter
    0.07
     مواطنة
    0.06
    Science
    0.06
    	ll
    0.06
    737
    0.06
     delve
    0.06
    -quarters
    0.06
     外部リンク
    0.06
     Neuroscience
    0.05
    微
    0.05
    Activations Density 0.000%

    No Known Activations