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. 80635
    Prev
    Next
    INDEX
    Explanations

    ist or twist

    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
     maneu
    -0.07
     precio
    -0.07
    	byte
    -0.06
     Baron
    -0.06
     (!$
    -0.06
    ("\(
    -0.06
    ombie
    -0.06
    首页
    -0.06
    Harry
    -0.06
    arehouse
    -0.06
    POSITIVE LOGITS
     twist
    0.15
     twists
    0.12
     Twist
    0.11
     twisted
    0.10
     twisting
    0.10
    Tw
    0.08
     TW
    0.08
     Tw
    0.08
     Swiss
    0.08
    _tw
    0.08
    Activations Density 0.005%

    No Known Activations