Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 83367
    Prev
    Next
    INDEX
    Explanations

    is

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rine
    -0.06
     назива
    -0.06
    ósito
    -0.06
    왔다
    -0.06
     staveb
    -0.06
    .templates
    -0.06
     sehr
    -0.06
     Eck
    -0.06
     چه
    -0.05
     گذاری
    -0.05
    POSITIVE LOGITS
     romantic
    0.08
    -stack
    0.07
    ipsis
    0.07
    -symbol
    0.06
    096
    0.06
    (pref
    0.06
     bids
    0.06
     Adv
    0.06
     dispatched
    0.06
     indebted
    0.06
    Activations Density 0.000%

    No Known Activations