© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 32539
    Prev
    Next
    INDEX
    Explanations

    controversial statements

    np_max-act · gemini-2.0-flash

    instances where the assistant gives a safety/disclaimer or refusal phrased as "As an AI language model..." and offers a hypothetical/example instead.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eros
    -0.07
    ной
    -0.06
    _SO
    -0.06
     therm
    -0.06
    _related
    -0.06
     Sanayi
    -0.06
    782
    -0.06
    -using
    -0.06
    .carousel
    -0.06
     excelente
    -0.05
    POSITIVE LOGITS
    исс
    0.07
     controversies
    0.07
     DMA
    0.06
    ॉट
    0.06
     напри
    0.06
    fasta
    0.06
     vacancies
    0.06
     giúp
    0.06
    _datas
    0.06
    ينية
    0.06
    Activations Density 0.129%

    No Known Activations