© 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 EvalsExportsinterp-engineNEWAPI 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. 95595
    Prev
    Next
    INDEX
    Explanations

    references to server-client interactions and authentication processes

    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
    izzo
    -0.07
    loyd
    -0.07
    سÙĨ
    -0.07
    buch
    -0.07
    ign
    -0.07
    illet
    -0.07
    pora
    -0.07
    curity
    -0.07
     <$>
    -0.07
    ovice
    -0.07
    POSITIVE LOGITS
     if
    0.16
     If
    0.15
    If
    0.13
    _if
    0.12
     nếu
    0.12
    	if
    0.11
    if
    0.11
     å¦Ĥæŀľ
    0.10
     еÑģли
    0.10
    -if
    0.10
    Activations Density 0.045%

    No Known Activations