© 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. 40976
    Prev
    Next
    INDEX
    Explanations

    references to collective understanding and evaluation of information in a field

    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
    £½
    -0.07
    ighthouse
    -0.06
    ioneer
    -0.06
    abeth
    -0.06
    SPAN
    -0.06
     noqa
    -0.05
    riteria
    -0.05
    å°ıå§IJ
    -0.05
    stoff
    -0.05
    Declared
    -0.05
    POSITIVE LOGITS
    oco
    0.07
    -"
    0.07
    ãĥ³ãĥĩãĤ£
    0.07
    alta
    0.06
    raf
    0.06
    chor
    0.06
     ÐŁÑĢа
    0.06
    hle
    0.06
    osto
    0.06
    dana
    0.06
    Activations Density 0.124%

    No Known Activations