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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28962
    Prev
    Next
    INDEX
    Explanations

    mentions of SharePoint and its related features

    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
     Yar
    -0.07
     test
    -0.06
    â̦
    -0.06
    baum
    -0.06
     fou
    -0.06
     tall
    -0.06
    akis
    -0.06
    ERE
    -0.06
     an
    -0.06
     h
    -0.05
    POSITIVE LOGITS
    ivec
    0.08
    ybrid
    0.07
    leÅŁik
    0.07
    à¹Īวมà¸ģ
    0.07
     tách
    0.07
    _TAC
    0.07
    обÑĢеÑĤ
    0.07
     withd
    0.07
    ounced
    0.07
    Disappear
    0.07
    Activations Density 0.011%

    No Known Activations