© 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. 104017
    Prev
    Next
    INDEX
    Explanations

    descriptions that evoke a sense of experience or atmosphere

    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
    одав
    -0.07
    awi
    -0.06
    osta
    -0.06
    perse
    -0.06
    cé
    -0.06
    asso
    -0.06
    iek
    -0.06
    eton
    -0.06
    zel
    -0.06
    kers
    -0.06
    POSITIVE LOGITS
     Rolls
    0.07
    úsqueda
    0.07
    .ActionListener
    0.07
    ë¡Ģ
    0.07
    _DS
    0.06
    PTY
    0.06
    rolls
    0.06
     ÐĶив
    0.06
    BorderStyle
    0.06
    Argb
    0.06
    Activations Density 0.021%

    No Known Activations