© 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. 61123
    Prev
    Next
    INDEX
    Explanations

    forms of the word "os" and its variations, likely targeting Spanish or Portuguese plural nouns

    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
    tr
    -0.10
    tem
    -0.10
    to
    -0.09
    ts
    -0.08
    um
    -0.08
    tele
    -0.08
    umar
    -0.08
    te
    -0.08
    adel
    -0.08
    hal
    -0.08
    POSITIVE LOGITS
    aurus
    0.10
    cean
    0.09
    dy
    0.08
    d
    0.08
    itory
    0.07
    otros
    0.07
    pheric
    0.07
    phere
    0.07
    serie
    0.07
    pective
    0.06
    Activations Density 0.061%

    No Known Activations