© 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. 9-LLAMASCOPE-RES-131K
    11. 96582
    Prev
    Next
    INDEX
    Explanations

    terms associated with disclaimers and limitations of liability

    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
    ’ta
    -0.07
    atto
    -0.06
    inki
    -0.06
    opup
    -0.06
     Perry
    -0.06
     stranded
    -0.06
    /install
    -0.06
     Gan
    -0.06
    hyth
    -0.05
    é«ĺæ¸ħ
    -0.05
    POSITIVE LOGITS
     jadx
    0.08
    زÙĩ
    0.07
    ارة
    0.07
    orgia
    0.07
    оÑī
    0.06
    ارات
    0.06
    agle
    0.06
    ãĤ§
    0.06
     anymore
    0.06
    sanitize
    0.06
    Activations Density 0.002%

    No Known Activations