© 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. 11-RESID-POST-AA
    11. 78239
    Prev
    Next
    INDEX
    Explanations

    standing or sitting

    np_max-act · gemini-2.0-flash

    content related to initiation rituals and group dynamics in a camp setting.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     ordinal
    -0.07
     zase
    -0.07
     Towards
    -0.07
    -core
    -0.06
     World
    -0.06
     thereafter
    -0.06
    rega
    -0.06
    /xml
    -0.06
     француз
    -0.06
     segue
    -0.06
    POSITIVE LOGITS
     standing
    0.09
     stood
    0.08
     sitting
    0.07
     sat
    0.07
     stands
    0.07
     stand
    0.07
    кт
    0.06
    ">↵↵
    0.06
     seated
    0.06
    stands
    0.06
    Activations Density 0.024%

    No Known Activations