© 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. 62378
    Prev
    Next
    INDEX
    Explanations

    dates within the text

    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
    etus
    -0.07
     лиÑĨ
    -0.07
     Harden
    -0.06
    ouver
    -0.06
    orary
    -0.06
    ira
    -0.06
     Rubin
    -0.06
     Clair
    -0.06
    eners
    -0.06
    engo
    -0.06
    POSITIVE LOGITS
     Fah
    0.06
    _fds
    0.06
    afc
    0.06
     пеÑĢеб
    0.06
    }elseif
    0.06
     Herman
    0.06
    ãĥŃãĥ³
    0.06
    arer
    0.06
    <tag
    0.06
     Millenn
    0.05
    Activations Density 0.007%

    No Known Activations