© 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. 71166
    Prev
    Next
    INDEX
    Explanations

    characteristics and measurements related to shapes and sizes

    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
    lush
    -0.07
    irates
    -0.07
    estate
    -0.07
    lint
    -0.07
    essages
    -0.06
    SqlCommand
    -0.06
    欣
    -0.06
    bsd
    -0.06
    asurer
    -0.06
    illy
    -0.06
    POSITIVE LOGITS
    ä¸Ķ
    0.08
     dunk
    0.07
    scape
    0.06
    .GetBytes
    0.06
     affair
    0.06
     except
    0.06
    entin
    0.06
    екÑĥ
    0.06
    ãĤ£
    0.06
     nhÆ°ng
    0.06
    Activations Density 0.008%

    No Known Activations