© 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. 118629
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer research and molecular biology

    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
    rio
    -0.08
     Hang
    -0.07
    _pdata
    -0.07
    Hang
    -0.07
    oin
    -0.06
    illon
    -0.06
     Hanging
    -0.06
     pů
    -0.06
     hang
    -0.06
    برÛĮ
    -0.06
    POSITIVE LOGITS
     targets
    0.13
     target
    0.13
    -target
    0.12
    target
    0.12
     Target
    0.11
     Targets
    0.11
    Target
    0.11
     targeting
    0.11
     targeted
    0.10
    .Target
    0.10
    Activations Density 0.012%

    No Known Activations