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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 40647
    Prev
    Next
    INDEX
    Explanations

    iment

    np_max-act · gemini-2.0-flash

    references to cellular characteristics and behaviors related to tissue regeneration and differentiation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of the protein name “vimentin,” picking up mentions of that intermediate‐filament marker in the text.

    oai_token-act-pair · o4-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
     corpor
    -0.07
    aurus
    -0.07
    iyim
    -0.07
     Wah
    -0.06
    MaxLength
    -0.06
    ランド
    -0.06
    균
    -0.06
    074
    -0.06
    коп
    -0.06
    calloc
    -0.06
    POSITIVE LOGITS
     hizo
    0.07
    ’ét
    0.07
    ryption
    0.06
     trademarks
    0.06
     warnings
    0.06
     Facebook
    0.06
     emotionally
    0.06
    MENT
    0.06
    hetic
    0.06
     additive
    0.06
    Activations Density 0.000%

    No Known Activations