© 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. 40302
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasts or comparisons

    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
    stants
    -0.06
    nder
    -0.06
    opoulos
    -0.06
    rup
    -0.06
    opus
    -0.06
    ading
    -0.05
    okie
    -0.05
    æīĭãĤĴ
    -0.05
     âĹİ
    -0.05
    hled
    -0.05
    POSITIVE LOGITS
     contrast
    0.12
     Contrast
    0.11
    contrast
    0.11
     contrasts
    0.07
    strand
    0.07
    ERM
    0.07
     stark
    0.07
    velt
    0.07
    uxtap
    0.07
    benh
    0.06
    Activations Density 0.013%

    No Known Activations