© 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. 60883
    Prev
    Next
    INDEX
    Explanations

    references to holes or gaps 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
    nen
    -0.09
    ement
    -0.08
    upply
    -0.07
    ovich
    -0.07
    ises
    -0.07
    elib
    -0.07
    OWL
    -0.07
    éĹĺ
    -0.07
    riel
    -0.07
    ially
    -0.07
    POSITIVE LOGITS
    iday
    0.09
    axed
    0.09
    omb
    0.08
    Å¡ov
    0.07
    hole
    0.07
    sworth
    0.07
     Hole
    0.07
    ocaust
    0.07
     drilled
    0.07
    ighb
    0.07
    Activations Density 0.009%

    No Known Activations