© 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. 55750
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational structure and roles

    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
    bstract
    -0.08
     ãĢ
    -0.07
    EEE
    -0.07
    quirer
    -0.07
    çIJ
    -0.07
    ospels
    -0.07
    .easy
    -0.07
     prob
    -0.07
    .AutoComplete
    -0.07
    ìĨ
    -0.07
    POSITIVE LOGITS
     the
    0.13
     The
    0.10
    ,the
    0.10
    the
    0.10
    The
    0.09
    	the
    0.09
    /the
    0.08
    _the
    0.08
    ÄĻk
    0.08
    âĢ¦the
    0.08
    Activations Density 0.261%

    No Known Activations