© 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 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. 84287
    Prev
    Next
    INDEX
    Explanations

    phrases indicating previous articles or content references

    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
    sworth
    -0.07
    deaux
    -0.07
    λε
    -0.06
    æĨ
    -0.06
    studio
    -0.06
    oku
    -0.06
    rightness
    -0.06
    coeff
    -0.06
    ctp
    -0.06
    edback
    -0.06
    POSITIVE LOGITS
    å²
    0.07
    wand
    0.07
    708
    0.07
     rib
    0.06
     íļĮ
    0.06
    머
    0.06
     bureaucr
    0.06
    ATH
    0.06
     oscill
    0.06
     rejection
    0.06
    Activations Density 0.002%

    No Known Activations