© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129225
    Prev
    Next
    INDEX
    Explanations

    references to same-sex relationships and marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iri
    -0.08
    Äį
    -0.07
    ÑģÑĮ
    -0.07
    trak
    -0.07
    hea
    -0.07
    upy
    -0.07
    resi
    -0.07
    ksen
    -0.07
    isel
    -0.07
    ุà¸ķ
    -0.07
    POSITIVE LOGITS
    PREC
    0.07
    uality
    0.06
    åľŃ
    0.06
     nÃło
    0.06
    ded
    0.06
    ameron
    0.06
     anywhere
    0.06
    es
    0.06
    Specifier
    0.06
    ORED
    0.06
    Activations Density 0.004%

    No Known Activations