© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125576
    Prev
    Next
    INDEX
    Explanations

    references to study abroad programs and related exchanges

    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
    ç´ł
    -0.07
    nal
    -0.07
    áli
    -0.06
    ãĤº
    -0.06
    orry
    -0.06
    cheng
    -0.06
    kv
    -0.06
    iras
    -0.06
    ullan
    -0.06
    orous
    -0.06
    POSITIVE LOGITS
    host
    0.07
     program
    0.07
     edil
    0.07
     experience
    0.07
    experience
    0.06
     experiences
    0.06
    681
    0.06
    ogue
    0.06
    rick
    0.06
    739
    0.06
    Activations Density 0.004%

    No Known Activations