© 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. 55097
    Prev
    Next
    INDEX
    Explanations

    references to specialized content or sections of a document

    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
    erson
    -0.08
    es
    -0.07
    rina
    -0.06
    ese
    -0.06
    enu
    -0.06
    ensex
    -0.06
     clue
    -0.06
     sept
    -0.06
     opposite
    -0.06
    etsk
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
     zdrav
    0.08
    ione
    0.08
    ius
    0.08
    ::|
    0.08
    ĮĴ
    0.07
    acles
    0.07
    kem
    0.07
    kop
    0.07
    ioxide
    0.07
    Activations Density 0.032%

    No Known Activations