© 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. 59271
    Prev
    Next
    INDEX
    Explanations

    terms related to standard procedures or expectations

    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
    ă
    -0.08
     ÑĤакÑĸ
    -0.07
    izzo
    -0.07
    yna
    -0.07
    лова
    -0.06
    rib
    -0.06
    رÙĥ
    -0.06
     иÑģполн
    -0.06
    cki
    -0.06
    -&
    -0.06
    POSITIVE LOGITS
    emey
    0.07
    rand
    0.07
    Wa
    0.06
    PTY
    0.06
     Wa
    0.06
     island
    0.06
     acronym
    0.06
    olest
    0.06
     seins
    0.06
     Ende
    0.06
    Activations Density 0.000%

    No Known Activations