© 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 EvalsExportsinterp-engineNEWAPI 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. 92084
    Prev
    Next
    INDEX
    Explanations

    terminology related to structure and organization

    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
    onis
    -0.07
    ingu
    -0.07
    617
    -0.07
    Į
    -0.07
     STATS
    -0.07
    quee
    -0.07
    venida
    -0.07
    ££
    -0.06
    agos
    -0.06
    Å
    -0.06
    POSITIVE LOGITS
     but
    0.10
    anda
    0.08
     sondern
    0.08
    but
    0.07
     nor
    0.07
     αλλά
    0.07
     pero
    0.07
    oplevel
    0.07
    ä½Ĩ
    0.06
     nhÆ°ng
    0.06
    Activations Density 0.007%

    No Known Activations