© 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. 94006
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research methodologies and treatments

    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
    -
    -0.06
    éķ
    -0.06
    logan
    -0.06
    ugg
    -0.06
    .
    -0.05
    ,
    -0.05
    "
    -0.05
     "
    -0.05
     individual
    -0.05
     jurisdiction
    -0.05
    POSITIVE LOGITS
    Å¡etÅĻ
    0.08
    quare
    0.08
     addCriterion
    0.08
    InParameter
    0.08
    енд
    0.08
     fi
    0.08
    ButtonTitles
    0.08
    ëį°ìĿ´íĬ¸
    0.08
    (æľ¨
    0.08
    inea
    0.08
    Activations Density 0.001%

    No Known Activations