© 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. 84548
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic and technology products

    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
     (
    -0.06
    loomberg
    -0.06
    ice
    -0.06
    lesi
    -0.06
    uddle
    -0.06
     next
    -0.05
    mour
    -0.05
    ETY
    -0.05
    okin
    -0.05
    alent
    -0.05
    POSITIVE LOGITS
     Uncategorized
    0.12
    leftright
    0.08
     Slider
    0.08
     Leave
    0.08
    elli
    0.07
     kategor
    0.07
    Leave
    0.07
    874
    0.07
    longleftrightarrow
    0.07
     tagged
    0.07
    Activations Density 0.033%

    No Known Activations