© 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. 87494
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the purpose or focus of a research study

    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
    æĥij
    -0.06
     dogs
    -0.06
    220
    -0.06
     hunts
    -0.06
    ording
    -0.06
     Hunt
    -0.06
    ulace
    -0.06
    avs
    -0.05
    agers
    -0.05
    ollah
    -0.05
    POSITIVE LOGITS
     paper
    0.13
     article
    0.13
    paper
    0.10
    .paper
    0.10
    -paper
    0.10
    article
    0.10
     Paper
    0.10
     study
    0.10
     Article
    0.10
    Paper
    0.10
    Activations Density 0.021%

    No Known Activations