© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127724
    Prev
    Next
    INDEX
    Explanations

    mentions of "men" and related terms across various contexts

    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
    genesis
    -0.08
    oslav
    -0.07
    eson
    -0.07
    tte
    -0.07
    ftar
    -0.07
    .GetObject
    -0.07
    eniz
    -0.07
    edin
    -0.07
    ahn
    -0.07
    aters
    -0.06
    POSITIVE LOGITS
    opause
    0.10
    endez
    0.09
    cken
    0.08
    ninger
    0.08
    aced
    0.08
    acing
    0.07
    roe
    0.07
    едж
    0.07
    ubar
    0.07
    folk
    0.07
    Activations Density 0.035%

    No Known Activations