© 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
    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. 35079
    Prev
    Next
    INDEX
    Explanations

    bases

    np_max-act · gemini-2.0-flash

    events or outcomes related to sports competitions.

    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
     스트
    -0.07
     منظور
    -0.07
     taps
    -0.06
    あの
    -0.06
     vůbec
    -0.06
     enlarg
    -0.06
     väl
    -0.06
    -headed
    -0.06
    ampled
    -0.06
    printStats
    -0.06
    POSITIVE LOGITS
     hereby
    0.06
     kan
    0.06
    .Se
    0.06
     Ku
    0.06
     USC
    0.06
    ]))↵
    0.06
    enus
    0.06
     Wie
    0.06
     Lak
    0.06
     Arb
    0.06
    Activations Density 0.002%

    No Known Activations