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. 123464
    Prev
    Next
    INDEX
    Explanations

    Into

    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
    miss
    -0.07
    .od
    -0.07
    廳
    -0.06
     Voc
    -0.06
     بار
    -0.06
     Erd
    -0.06
    제
    -0.06
     червня
    -0.06
     пас
    -0.06
    绍
    -0.06
    POSITIVE LOGITS
    cheduled
    0.07
    Nb
    0.07
     серд
    0.06
    xxxxxxxx
    0.06
    plementary
    0.06
    };
    ↵
    ↵
    0.06
     complete
    0.06
     debt
    0.06
     pomáh
    0.06
    _ALLOW
    0.06
    Activations Density 0.001%

    No Known Activations