© 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. 81788
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "using" in code or technical documentation

    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
    roud
    -0.08
    _PL
    -0.07
    onga
    -0.07
    RLF
    -0.07
    iao
    -0.07
    unar
    -0.07
    ÑĢÑĸз
    -0.07
    .lex
    -0.07
    assage
    -0.06
    zi
    -0.06
    POSITIVE LOGITS
    827
    0.06
    uction
    0.06
    DT
    0.06
    _exempt
    0.06
    itia
    0.06
     Gate
    0.05
    386
    0.05
    ãĥ¥
    0.05
    ivery
    0.05
    oulos
    0.05
    Activations Density 0.001%

    No Known Activations