© 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. 56369
    Prev
    Next
    INDEX
    Explanations

    references to specific instances or examples in the text

    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
     Sherman
    -0.06
     powerful
    -0.06
    713
    -0.06
    eni
    -0.05
    of
    -0.05
    ·
    -0.05
     stabil
    -0.05
     Indies
    -0.05
    âĤ
    -0.05
     osm
    -0.05
    POSITIVE LOGITS
    peon
    0.08
    kün
    0.08
    VOKE
    0.08
    iyon
    0.08
    fuse
    0.08
    abyrin
    0.07
    uien
    0.07
    iversite
    0.07
    abar
    0.07
    abyrinth
    0.07
    Activations Density 0.039%

    No Known Activations