© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106525
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of receiving and handling information or communication

    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
    _SRC
    -0.06
    aye
    -0.06
    \"
    -0.06
    REW
    -0.06
    Ñģп
    -0.06
    xc
    -0.06
    illa
    -0.06
    iral
    -0.06
    l
    -0.06
    ume
    -0.06
    POSITIVE LOGITS
    DCALL
    0.09
    ainers
    0.07
    /respond
    0.07
    /send
    0.07
    âķĿ
    0.07
    bles
    0.07
    /trans
    0.07
    gaben
    0.06
    <boost
    0.06
    /report
    0.06
    Activations Density 0.022%

    No Known Activations