© 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. 129022
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and systems, particularly in health and environment contexts

    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
    kola
    -0.06
    ละ
    -0.06
    chw
    -0.06
     è¾
    -0.06
    ãĥ¼ãĥ
    -0.06
    apult
    -0.06
     Gim
    -0.06
     laid
    -0.06
    åĨ¬
    -0.06
    beer
    -0.06
    POSITIVE LOGITS
    /Sub
    0.13
    (Sub
    0.12
    /sub
    0.10
    =sub
    0.09
    .Sub
    0.09
    (sub
    0.08
     sub
    0.08
    _Sub
    0.08
    _codegen
    0.07
     Gale
    0.07
    Activations Density 0.042%

    No Known Activations