© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57087
    Prev
    Next
    INDEX
    Explanations

    references to various types of grids and grid-related concepts

    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
     esl
    -0.07
    esses
    -0.07
    aad
    -0.07
    oded
    -0.07
     sworn
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    æĹıèĩªæ²»
    -0.07
    -même
    -0.06
    bject
    -0.06
    ariat
    -0.06
    POSITIVE LOGITS
    iron
    0.09
    /grid
    0.09
    lock
    0.08
    works
    0.08
    y
    0.08
    -wide
    0.08
    locked
    0.07
    wide
    0.07
    work
    0.07
    roots
    0.07
    Activations Density 0.022%

    No Known Activations