© 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. 40172
    Prev
    Next
    INDEX
    Explanations

    conditional phrases related to timing or conditions

    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
    ave
    -0.07
    uml
    -0.07
    aux
    -0.07
    actual
    -0.07
    utzer
    -0.06
     engel
    -0.06
    erialized
    -0.06
    lia
    -0.06
    InternalServerError
    -0.06
    posable
    -0.06
    POSITIVE LOGITS
     spread
    0.07
     compared
    0.07
     accompanied
    0.07
     used
    0.07
     properly
    0.07
     ing
    0.06
    iesen
    0.06
    wing
    0.06
     viewed
    0.06
     run
    0.06
    Activations Density 0.024%

    No Known Activations