© 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. 15-LLAMASCOPE-RES-131K
    11. 999
    Prev
    Next
    INDEX
    Explanations

    discussions related to constraints and parameters in mathematical or scientific 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
    wich
    -0.08
    ulu
    -0.07
    agr
    -0.07
    rab
    -0.07
    ADR
    -0.06
    ifo
    -0.06
    adil
    -0.06
    weis
    -0.06
    à¹Ħว
    -0.06
    ativ
    -0.06
    POSITIVE LOGITS
     redundant
    0.07
    PerPixel
    0.07
     Mort
    0.07
    ëĵĿ
    0.07
    _least
    0.07
     free
    0.06
    ndata
    0.06
     Gra
    0.06
    /Foundation
    0.06
     rigid
    0.06
    Activations Density 0.069%

    No Known Activations