© 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. 9-LLAMASCOPE-RES-131K
    11. 98840
    Prev
    Next
    INDEX
    Explanations

    references to web comments and scripting components

    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
    ersistent
    -0.07
    astic
    -0.07
    afen
    -0.07
    ège
    -0.07
    angan
    -0.07
    ope
    -0.06
    afe
    -0.06
    uffman
    -0.06
    eniable
    -0.06
    erosis
    -0.06
    POSITIVE LOGITS
    (Me
    0.07
     глÑĥ
    0.07
    еÑģи
    0.07
    ENCED
    0.06
    210
    0.06
     Trident
    0.06
    ायत
    0.06
     ÑħозÑı
    0.06
    仲
    0.06
    ROWSER
    0.06
    Activations Density 0.000%

    No Known Activations