© 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. 71471
    Prev
    Next
    INDEX
    Explanations

    references to gendered individuals and their roles in narratives

    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
    agina
    -0.08
    lech
    -0.07
     themselves
    -0.07
    illow
    -0.06
     itself
    -0.06
     personalities
    -0.06
    acher
    -0.06
    mae
    -0.06
    ÑģÑĤиÑĤ
    -0.06
    .Static
    -0.05
    POSITIVE LOGITS
     whose
    0.09
     who
    0.09
    whose
    0.09
    عاÙĨ
    0.08
    brains
    0.07
    umpt
    0.07
     whom
    0.07
    hattan
    0.07
    åĽ£
    0.07
    UnderTest
    0.06
    Activations Density 0.026%

    No Known Activations