© 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. 87661
    Prev
    Next
    INDEX
    Explanations

    characteristics of technology or mechanical features

    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
    umi
    -0.06
     Valid
    -0.06
    ined
    -0.06
     zwar
    -0.06
     Erg
    -0.06
    Ĥ¹
    -0.06
    gue
    -0.06
    ammad
    -0.06
     Enough
    -0.06
    æº
    -0.06
    POSITIVE LOGITS
    PerPixel
    0.07
    Trap
    0.07
    à¤Ĥà¤Ń
    0.07
    nave
    0.07
    itos
    0.07
    ua
    0.07
    wyn
    0.07
    Vien
    0.06
    ivec
    0.06
    -scalable
    0.06
    Activations Density 0.020%

    No Known Activations