© 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. 126342
    Prev
    Next
    INDEX
    Explanations

    mentions of various forms of the word "leg."

    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
    jsc
    -0.06
    иÑĤоÑĢ
    -0.06
    ÑģÑı
    -0.06
    etry
    -0.06
    иÑģÑģ
    -0.06
    å°½
    -0.06
    apas
    -0.06
    eties
    -0.06
    iffe
    -0.06
    stry
    -0.06
    POSITIVE LOGITS
    itimate
    0.10
    islation
    0.08
    gett
    0.08
    gers
    0.07
    finity
    0.07
    -leg
    0.07
    reta
    0.07
    imized
    0.07
    atures
    0.07
    endar
    0.07
    Activations Density 0.006%

    No Known Activations