© 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. 70996
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or organizations

    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
    mts
    -0.07
    alama
    -0.07
    'gc
    -0.07
    walker
    -0.06
    weis
    -0.06
     далÑĸ
    -0.06
    (Self
    -0.06
    OLS
    -0.06
    GNU
    -0.06
    tiles
    -0.06
    POSITIVE LOGITS
     FLASH
    0.07
    ONA
    0.07
    ona
    0.06
     yesterday
    0.06
     dispatch
    0.06
     Dispatch
    0.06
     Princip
    0.06
    piler
    0.06
     Flash
    0.05
    nia
    0.05
    Activations Density 0.014%

    No Known Activations