© 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. 76219
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational goals and priorities

    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
    ishly
    -0.08
    åħį
    -0.07
    ajs
    -0.07
    chestra
    -0.07
    ish
    -0.07
    shima
    -0.07
    tas
    -0.07
    zim
    -0.07
    ppard
    -0.07
    MAND
    -0.07
    POSITIVE LOGITS
     focus
    0.08
    able
    0.08
     Focus
    0.08
     shifted
    0.08
    focus
    0.07
     shift
    0.07
     Shift
    0.07
    shift
    0.07
    Shift
    0.07
    -focus
    0.07
    Activations Density 0.010%

    No Known Activations