© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123066
    Prev
    Next
    INDEX
    Explanations

    story

    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
    ête
    -0.07
    .collider
    -0.07
    _peak
    -0.07
     odpad
    -0.06
     greedy
    -0.06
     lương
    -0.06
     Tomas
    -0.06
     hafta
    -0.06
     FindObjectOfType
    -0.06
    asthan
    -0.06
    POSITIVE LOGITS
     story
    0.08
    _variables
    0.06
    Parser
    0.06
     Secret
    0.06
     Wheel
    0.06
     Story
    0.06
    -mail
    0.06
    ListComponent
    0.06
    statuses
    0.06
    乘
    0.06
    Activations Density 0.009%

    No Known Activations