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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 62535
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a basis or orientation for analysis or actions

    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
    iy
    -0.07
    uil
    -0.07
    hog
    -0.06
    arie
    -0.06
    ol
    -0.06
    ÅĻil
    -0.06
    el
    -0.06
    ubi
    -0.06
    ãĥ«ãģ®
    -0.06
     verm
    -0.06
    POSITIVE LOGITS
    edBy
    0.09
    ependency
    0.07
    ropdown
    0.07
    rvine
    0.07
    prus
    0.07
    rieve
    0.07
    irectory
    0.07
    edException
    0.06
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.06
    .say
    0.06
    Activations Density 0.039%

    No Known Activations