© 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. 73245
    Prev
    Next
    INDEX
    Explanations

    descriptions of astronomical images

    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
     simply
    -0.07
    stell
    -0.06
     sovereign
    -0.06
    llu
    -0.05
     yet
    -0.05
    hide
    -0.05
    ide
    -0.05
     millennium
    -0.05
    avig
    -0.05
     once
    -0.05
    POSITIVE LOGITS
    abcdefghijkl
    0.08
    Äįást
    0.08
    ''''
    0.07
    bounce
    0.07
    lém
    0.07
    oÅĪ
    0.07
    /people
    0.07
     upset
    0.07
     VÅ¡
    0.07
     rows
    0.07
    Activations Density 0.004%

    No Known Activations