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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29727
    Prev
    Next
    INDEX
    Explanations

    attributes related to lightweight characteristics in products

    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
    idth
    -0.09
    ptime
    -0.07
    θεν
    -0.07
    Ñİк
    -0.07
    onical
    -0.07
    λÏħ
    -0.07
     lá»ĩnh
    -0.07
    ätt
    -0.07
    atically
    -0.07
    deg
    -0.07
    POSITIVE LOGITS
    -weight
    0.09
    ed
    0.08
    ening
    0.08
    /light
    0.07
     lighter
    0.07
     yet
    0.07
    lifting
    0.07
    ened
    0.07
     weight
    0.07
    ning
    0.07
    Activations Density 0.007%

    No Known Activations