© 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. 22-LLAMASCOPE-RES-131K
    11. 4048
    Prev
    Next
    INDEX
    Explanations

    references to the actions of switching something on or off

    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
    uxt
    -0.07
    led
    -0.07
    onium
    -0.07
    les
    -0.07
    issant
    -0.06
    cape
    -0.06
    ante
    -0.06
    arily
    -0.06
     Sle
    -0.06
    atum
    -0.06
    POSITIVE LOGITS
    retorno
    0.07
    onto
    0.06
    ikal
    0.06
    -urlencoded
    0.06
    ibel
    0.06
    338
    0.06
    metis
    0.06
     Ont
    0.06
    Axes
    0.06
    ná
    0.06
    Activations Density 0.025%

    No Known Activations