© 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 EvalsExportsinterp-engineNEWAPI 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. 4997
    Prev
    Next
    INDEX
    Explanations

    code structure elements and syntax

    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
    lant
    -0.08
    omon
    -0.07
    Calibri
    -0.07
    emouth
    -0.07
    ACHI
    -0.07
    ìĥī
    -0.06
     YYS
    -0.06
    icide
    -0.06
    enor
    -0.06
    @mail
    -0.06
    POSITIVE LOGITS
    ork
    0.07
    azzi
    0.07
    unction
    0.07
     Similarly
    0.07
     similarly
    0.06
    Similarly
    0.06
    trad
    0.06
    stub
    0.06
    edia
    0.06
    rat
    0.06
    Activations Density 0.062%

    No Known Activations