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. 104152
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
     nrows
    -0.07
     kem
    -0.07
    484
    -0.06
    uan
    -0.06
     Avengers
    -0.06
    otic
    -0.06
    .Enc
    -0.06
     calloc
    -0.06
    設定
    -0.06
     heute
    -0.06
    POSITIVE LOGITS
     |=
    0.06
    MediaType
    0.06
     audible
    0.06
    yectos
    0.06
    ='',↵
    0.06
    vision
    0.06
    cılık
    0.06
    .toolStripMenuItem
    0.06
    ả
    0.06
     tüket
    0.06
    Activations Density 0.020%

    No Known Activations