© 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. 28950
    Prev
    Next
    INDEX
    Explanations

    words related to specific classifications or scientific categories

    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
    ajas
    -0.07
    legg
    -0.07
    ollen
    -0.07
    ypi
    -0.07
    ateg
    -0.06
    iegel
    -0.06
    upe
    -0.06
     Carl
    -0.06
    azor
    -0.06
    ause
    -0.06
    POSITIVE LOGITS
    ardy
    0.07
    wn
    0.07
     addCriterion
    0.07
     Ðļа
    0.06
    urret
    0.06
    ürn
    0.06
    rix
    0.06
    279
    0.06
    мен
    0.06
    ogan
    0.06
    Activations Density 0.041%

    No Known Activations