© 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. 61121
    Prev
    Next
    INDEX
    Explanations

    technical terms and names related to technology and ecommerce

    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
    afx
    -0.07
    ActionCreators
    -0.07
    .scalablytyped
    -0.06
    hv
    -0.06
     бÑĥк
    -0.06
    usat
    -0.06
     till
    -0.06
    osaur
    -0.06
    aminer
    -0.06
    510
    -0.06
    POSITIVE LOGITS
    \Module
    0.06
    lename
    0.06
    ábado
    0.06
     kre
    0.06
    var
    0.06
    isch
    0.06
    ãĥ¼ãĥ
    0.06
    prung
    0.06
     Peach
    0.06
    odie
    0.06
    Activations Density 0.000%

    No Known Activations