© 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. 125410
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mate" in 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
    naire
    -0.08
    orie
    -0.07
    itzer
    -0.07
    ahy
    -0.07
    .DEFINE
    -0.07
    aire
    -0.07
    itz
    -0.07
    atti
    -0.07
    rud
    -0.07
    nout
    -0.07
    POSITIVE LOGITS
    usz
    0.09
    ernal
    0.07
    y
    0.07
    RED
    0.07
    oom
    0.07
    ENS
    0.06
    ings
    0.06
    st
    0.06
    ingle
    0.06
    illard
    0.06
    Activations Density 0.003%

    No Known Activations