© 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. 85077
    Prev
    Next
    INDEX
    Explanations

    references to the success and accomplishments of the community or institution

    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
     pen
    -0.06
    ,
    -0.06
     and
    -0.06
     eng
    -0.06
     pet
    -0.06
    -
    -0.06
    eres
    -0.05
    .
    -0.05
    pen
    -0.05
     or
    -0.05
    POSITIVE LOGITS
    unsch
    0.08
    roken
    0.08
    ffa
    0.08
    openh
    0.07
    ritel
    0.07
    aria
    0.07
    nickname
    0.07
    -events
    0.07
    uffs
    0.07
    ucker
    0.07
    Activations Density 0.019%

    No Known Activations