© 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. 97261
    Prev
    Next
    INDEX
    Explanations

    imports from the React library in code snippets

    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
    icated
    -0.06
    á»ģn
    -0.06
    omu
    -0.06
    èn
    -0.06
    ething
    -0.06
    obook
    -0.06
    ochrome
    -0.06
    reen
    -0.06
    cion
    -0.06
    romise
    -0.05
    POSITIVE LOGITS
    ibold
    0.07
    OMB
    0.07
    omb
    0.07
    ìĿ¸ëį°
    0.07
    atas
    0.07
    pard
    0.06
    _VC
    0.06
    eo
    0.06
    æķ
    0.06
    chl
    0.06
    Activations Density 0.000%

    No Known Activations