© 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. 84785
    Prev
    Next
    INDEX
    Explanations

    references to discussions about horses and related media such as interviews and programs

    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
    ANTE
    -0.07
    erosis
    -0.07
    abus
    -0.07
    eldorf
    -0.07
    icari
    -0.07
    алом
    -0.07
    okers
    -0.07
    aoke
    -0.07
    aka
    -0.06
    adge
    -0.06
    POSITIVE LOGITS
     someone
    0.07
    someone
    0.07
    æľī人
    0.07
     пÑĸдÑģ
    0.07
    ENCHMARK
    0.06
     STATES
    0.06
    *)((
    0.06
    claims
    0.06
     claims
    0.06
    -http
    0.06
    Activations Density 0.042%

    No Known Activations