© 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. 118730
    Prev
    Next
    INDEX
    Explanations

    references to education and educational programs

    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
    laus
    -0.09
    bis
    -0.07
    iding
    -0.07
    uel
    -0.07
    acl
    -0.07
    ساÙħ
    -0.06
    еÑĢв
    -0.06
    eto
    -0.06
    agination
    -0.06
    isk
    -0.06
    POSITIVE LOGITS
    ally
    0.14
    /testing
    0.10
    ALLY
    0.10
    cação
    0.10
    /Instruction
    0.10
    èĢħçļĦ
    0.09
    tainment
    0.09
    taire
    0.09
    æĸĻçĦ¡æĸĻ
    0.08
    gamber
    0.08
    Activations Density 0.036%

    No Known Activations