© 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. 121782
    Prev
    Next
    INDEX
    Explanations

    way

    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
    -cond
    -0.07
     regulation
    -0.07
    _predicate
    -0.07
    ARGE
    -0.07
     आल
    -0.07
     criterion
    -0.07
     Zones
    -0.06
    iro
    -0.06
     notably
    -0.06
    ople
    -0.06
    POSITIVE LOGITS
    	Session
    0.07
     "*"
    0.07
     Hulk
    0.06
    _refs
    0.06
    uesday
    0.06
    isActive
    0.06
     Hük
    0.06
    /blog
    0.06
     Monday
    0.06
     انواع
    0.06
    Activations Density 0.046%

    No Known Activations