© 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. 31297
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific testing or experimentation

    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
    quential
    -0.07
    Ľi
    -0.07
    peare
    -0.07
    ossil
    -0.07
     æ°
    -0.07
    owel
    -0.07
    mey
    -0.06
     Sexe
    -0.06
    redo
    -0.06
    ecycle
    -0.06
    POSITIVE LOGITS
     CNS
    0.06
     cessation
    0.06
    vertime
    0.06
    (ib
    0.06
     Luk
    0.06
    ustral
    0.06
     ones
    0.06
     modern
    0.05
     genu
    0.05
    CTS
    0.05
    Activations Density 0.000%

    No Known Activations