© 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. 87916
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or subjects within the text

    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
    ÙĪار
    -0.07
    rif
    -0.07
    que
    -0.07
    orial
    -0.06
    -bin
    -0.06
     Pey
    -0.06
    ette
    -0.06
     dawn
    -0.06
    adr
    -0.06
    urus
    -0.06
    POSITIVE LOGITS
     behalf
    0.10
     occasion
    0.08
     basis
    0.07
    basis
    0.07
    angel
    0.07
    occasion
    0.07
    _basis
    0.07
    cale
    0.06
    imb
    0.06
    OPS
    0.06
    Activations Density 0.009%

    No Known Activations