© 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. 17-LLAMASCOPE-RES-131K
    11. 74270
    Prev
    Next
    INDEX
    Explanations

    references to character sets and file permissions

    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
    olf
    -0.07
    hibition
    -0.06
    uro
    -0.06
    ohn
    -0.06
    aven
    -0.06
    erg
    -0.06
    essor
    -0.06
    regunta
    -0.06
    /import
    -0.06
    er
    -0.05
    POSITIVE LOGITS
    =UTF
    0.10
    ucks
    0.10
    =utf
    0.09
    AGMA
    0.08
    ted
    0.08
    ient
    0.07
    igor
    0.07
    ped
    0.07
    anza
    0.07
    ÅĽci
    0.07
    Activations Density 0.001%

    No Known Activations