© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    references to instructional or informative content

    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
    inv
    -0.06
    -0.05
     post
    -0.05
     HE
    -0.05
    burn
    -0.05
    θÏħ
    -0.05
     se
    -0.05
    uder
    -0.05
     tam
    -0.05
    under
    -0.05
    POSITIVE LOGITS
     кни
    0.09
     book
    0.08
     bì
    0.08
    recommended
    0.08
    olib
    0.07
    jte
    0.07
    åľ¨çº¿éĺħ读
    0.07
    -book
    0.07
    ãĥĩãĤ£ãĥ¼ãĤ¹
    0.07
     thầu
    0.07
    Activations Density 0.021%

    No Known Activations