© 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. 74860
    Prev
    Next
    INDEX
    Explanations

    suggestions for environmentally friendly actions

    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
    nut
    -0.07
    stable
    -0.06
    aunch
    -0.06
     Stability
    -0.06
    umping
    -0.06
    ibling
    -0.06
    nuts
    -0.06
    achine
    -0.06
    upy
    -0.06
     stability
    -0.06
    POSITIVE LOGITS
     lifestyle
    0.09
     household
    0.08
     living
    0.08
     personal
    0.08
    çĴ°
    0.07
     habits
    0.07
    663
    0.07
     Household
    0.07
     Leak
    0.07
     everyday
    0.07
    Activations Density 0.022%

    No Known Activations