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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 75467
    Prev
    Next
    INDEX
    Explanations

    nP

    np_max-act · gemini-2.0-flash

    scientific terms and chemical compounds related to photodynamic therapy and their properties.

    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
     ############
    -0.06
     realiz
    -0.06
    32
    -0.06
     tether
    -0.06
     entrances
    -0.06
    50
    -0.06
    acidad
    -0.06
     sided
    -0.06
    ็นท
    -0.06
     thus
    -0.06
    POSITIVE LOGITS
    ap
    0.17
    p
    0.17
    AP
    0.15
    ip
    0.14
    pp
    0.14
    P
    0.14
    pe
    0.13
     JP
    0.13
    OP
    0.13
    п
    0.13
    Activations Density 0.691%

    No Known Activations