© 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. 76688
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a comparison or distinction between 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
     Rat
    -0.06
    ugh
    -0.06
    via
    -0.06
    ovic
    -0.06
    ree
    -0.06
    legg
    -0.06
    ading
    -0.06
    antz
    -0.06
    issen
    -0.06
    ivot
    -0.06
    POSITIVE LOGITS
     between
    0.10
     Between
    0.09
     междÑĥ
    0.09
    between
    0.08
    Between
    0.08
     giữa
    0.08
     BETWEEN
    0.08
     difference
    0.07
    difference
    0.07
     tussen
    0.07
    Activations Density 0.004%

    No Known Activations