© 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. 123154
    Prev
    Next
    INDEX
    Explanations

    h

    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
     attendant
    -0.07
     vou
    -0.06
    řeba
    -0.06
     unst
    -0.06
     reproductive
    -0.06
     فقد
    -0.06
     prz
    -0.06
     coal
    -0.06
     nepří
    -0.06
     równ
    -0.06
    POSITIVE LOGITS
    h
    0.12
    hs
    0.07
    hk
    0.06
     dn
    0.06
    스
    0.06
    hi
    0.06
    	sh
    0.06
    mus
    0.06
    apiKey
    0.06
    (h
    0.06
    Activations Density 0.004%

    No Known Activations