© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129217
    Prev
    Next
    INDEX
    Explanations

    references to metrics and comparisons related to numeric data or statistics

    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
    892
    -0.06
    arro
    -0.06
    890
    -0.06
     shown
    -0.06
    862
    -0.06
    etter
    -0.05
    857
    -0.05
    ANGED
    -0.05
    ulla
    -0.05
    vert
    -0.05
    POSITIVE LOGITS
    ież
    0.07
    ynn
    0.07
    ERNEL
    0.07
     evolution
    0.07
    ATER
    0.07
    isay
    0.07
     Weiner
    0.07
     kontakte
    0.06
    och
    0.06
    adge
    0.06
    Activations Density 0.007%

    No Known Activations