© 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. 123925
    Prev
    Next
    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash

    information related to the historical background and achievements of chemical companies.

    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
     Gul
    -0.07
    203
    -0.06
     Buk
    -0.06
     Lucy
    -0.06
     Ark
    -0.06
     Kul
    -0.06
     speculated
    -0.06
     Gut
    -0.06
    (ab
    -0.06
     Uz
    -0.06
    POSITIVE LOGITS
     performance
    0.17
     Performance
    0.15
    Performance
    0.13
    performance
    0.12
     PERFORMANCE
    0.11
     performances
    0.11
    -performance
    0.10
     performers
    0.09
    연
    0.09
    能力
    0.08
    Activations Density 0.054%

    No Known Activations