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. 104119
    Prev
    Next
    INDEX
    Explanations

    line

    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
    ovaného
    -0.07
    patients
    -0.07
     —↵↵
    -0.07
    +-+-+-+-
    -0.06
     daha
    -0.06
     lineno
    -0.06
    علوم
    -0.06
     constituted
    -0.06
    ﺪ
    -0.06
     meds
    -0.06
    POSITIVE LOGITS
    _ENDIAN
    0.07
    _sock
    0.07
    -next
    0.06
    .Val
    0.06
     трет
    0.06
     авт
    0.06
     lan
    0.06
    ฤด
    0.06
    .ast
    0.06
     раст
    0.06
    Activations Density 0.010%

    No Known Activations