© 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. 83977
    Prev
    Next
    INDEX
    Explanations

    elements related to competitive events or rankings

    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
    -
    -0.07
    Ì
    -0.06
     import
    -0.06
    bet
    -0.06
     HuffPost
    -0.06
     pillar
    -0.06
     hete
    -0.06
     Jonas
    -0.05
     nameof
    -0.05
    bes
    -0.05
    POSITIVE LOGITS
    apon
    0.07
     addCriterion
    0.07
    arget
    0.07
    anten
    0.07
     âĹĦ
    0.07
    GuidId
    0.07
    orp
    0.07
    agine
    0.07
    lements
    0.07
    enment
    0.06
    Activations Density 0.005%

    No Known Activations