© 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. 87334
    Prev
    Next
    INDEX
    Explanations

    references to official meetings and statements from legislative bodies

    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
     Kay
    -0.07
     поÑĪ
    -0.06
    Kay
    -0.06
    ouis
    -0.06
    opoulos
    -0.06
    RefPtr
    -0.06
    317
    -0.05
     foresee
    -0.05
     Saudis
    -0.05
    -uri
    -0.05
    POSITIVE LOGITS
    andal
    0.07
     metav
    0.07
    utto
    0.07
     DESC
    0.07
    urette
    0.07
    asje
    0.07
    bor
    0.07
    pees
    0.07
     Slav
    0.06
    æ·
    0.06
    Activations Density 0.021%

    No Known Activations