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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83581
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons, rankings, or assessments of quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Academic hedging phrases that authors use to qualify claims of novelty or knowledge limitations, typically variations of "to the best of our/my knowledge" or "that we/I know of".

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    596
    -0.07
    ghest
    -0.06
     Ðļоли
    -0.06
    818
    -0.06
    214
    -0.06
    ASH
    -0.06
     Piper
    -0.06
    dre
    -0.06
    ä»ĺãģį
    -0.06
     ber
    -0.06
    POSITIVE LOGITS
     known
    0.09
     I
    0.08
    known
    0.07
     according
    0.07
    KNOWN
    0.07
    ograd
    0.07
     æį
    0.07
    inn
    0.07
     çŁ¥
    0.07
     Known
    0.07
    Activations Density 0.139%

    No Known Activations