Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 22539
    Prev
    Next
    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash

    technical concepts related to mathematical modeling and systems dynamics.

    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
     продаж
    -0.07
    شار
    -0.06
    ski
    -0.06
    xious
    -0.06
    _detach
    -0.06
     свід
    -0.06
    _pro
    -0.06
     Vic
    -0.06
    ManagerInterface
    -0.06
    uchen
    -0.06
    POSITIVE LOGITS
    	token
    0.07
     persisted
    0.06
     arc
    0.06
     am
    0.06
    am
    0.06
    raw
    0.06
    počet
    0.06
    (price
    0.06
     ASM
    0.06
    IRST
    0.06
    Activations Density 0.000%

    No Known Activations