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. 111661
    Prev
    Next
    INDEX
    Explanations

    stating

    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
    finder
    -0.06
    firebase
    -0.06
     نيز
    -0.06
     Imagine
    -0.06
     amnesty
    -0.06
    ember
    -0.06
     نمای
    -0.06
    blind
    -0.06
     nutrients
    -0.06
     grey
    -0.06
    POSITIVE LOGITS
     stated
    0.11
     stating
    0.09
     Patel
    0.08
     Ст
    0.08
    _Output
    0.07
     addressing
    0.07
     titled
    0.07
     startIndex
    0.07
    ΜΑ
    0.06
    -st
    0.06
    Activations Density 0.010%

    No Known Activations