© 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. 15-LLAMASCOPE-RES-131K
    6. 90235
    Prev
    Next
    INDEX
    Explanations

    mentions of floor-related terms in various contexts

    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
    ew
    -0.08
    TREE
    -0.07
    es
    -0.07
    ess
    -0.07
    eld
    -0.07
    ãģ¦
    -0.06
    urers
    -0.06
    ILT
    -0.06
    eer
    -0.06
     proven
    -0.06
    POSITIVE LOGITS
    boards
    0.08
     Dahl
    0.08
    ings
    0.08
    erd
    0.07
    ongan
    0.07
    lift
    0.07
    itzer
    0.07
    ictures
    0.07
    -mounted
    0.07
    ways
    0.07
    Activations Density 0.015%

    No Known Activations