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. 11-RESID-POST-AA
    6. 80894
    Prev
    Next
    INDEX
    Explanations

    relationships

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -android
    -0.08
     Pe
    -0.07
     RB
    -0.07
    .notify
    -0.07
     larg
    -0.07
    Cre
    -0.06
    -pe
    -0.06
    ephy
    -0.06
     Pav
    -0.06
    (rb
    -0.06
    POSITIVE LOGITS
    "/>
    ↵
    0.07
    เทศ
    0.07
    洲
    0.06
     zaměstn
    0.06
    >
    ↵
    ↵
    0.06
    }↵↵↵↵↵
    0.06
     περιο
    0.06
    SYM
    0.06
    ються
    0.06
     будуть
    0.06
    Activations Density 0.028%

    No Known Activations