© 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. 84694
    Prev
    Next
    INDEX
    Explanations

    references to specific laws and regulations

    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
    LastError
    -0.07
    ायà¤ķ
    -0.07
    exus
    -0.06
    ãģĩ
    -0.06
    Nib
    -0.06
     Pace
    -0.06
     already
    -0.06
    оваÑħ
    -0.06
    oren
    -0.06
     Nas
    -0.06
    POSITIVE LOGITS
    .gs
    0.06
     founders
    0.06
    ourd
    0.06
    rador
    0.06
    erner
    0.06
    lections
    0.06
    231
    0.06
    isters
    0.06
    ãĥ³ãĥĹ
    0.06
    cott
    0.06
    Activations Density 0.026%

    No Known Activations