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. 3-RESID-POST-AA
    6. 94587
    Prev
    Next
    INDEX
    Explanations

    plan

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.07
    atori
    -0.07
     أمر
    -0.06
    丘
    -0.06
    _weak
    -0.06
    見
    -0.06
     unlimited
    -0.06
    іст
    -0.06
    especially
    -0.06
    >/
    -0.06
    POSITIVE LOGITS
     plan
    0.12
     plans
    0.11
     planning
    0.11
     Plans
    0.10
    Plans
    0.08
     Place
    0.07
     PL
    0.07
     Bars
    0.07
     Plan
    0.07
    pora
    0.07
    Activations Density 0.011%

    No Known Activations