© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13632
    Prev
    Next
    INDEX
    Explanations

    anking

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming genomic sequence regions or features (e.g. upstream, flanking, exon, intron, UTR).

    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
    }`}>↵
    -0.07
     airline
    -0.06
     shimmer
    -0.06
    alardan
    -0.06
    berapa
    -0.06
     toured
    -0.06
    >N
    -0.06
    organized
    -0.06
    .INPUT
    -0.06
     spectacle
    -0.06
    POSITIVE LOGITS
     야
    0.07
    .Qu
    0.07
     ミ
    0.07
    най
    0.06
    oir
    0.06
    iban
    0.06
    eden
    0.06
     chuyện
    0.06
    .impl
    0.06
    !」↵↵
    0.06
    Activations Density 0.006%

    No Known Activations