© 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. 62071
    Prev
    Next
    INDEX
    Explanations

    references to artistic elements or styles

    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
    edd
    -0.07
    edx
    -0.07
     pedest
    -0.07
    bai
    -0.07
    å¾ĴæŃ©
    -0.07
    edback
    -0.07
    ìĺ
    -0.07
    icot
    -0.07
    qe
    -0.07
    teri
    -0.07
    POSITIVE LOGITS
    077
    0.06
    312
    0.06
    unc
    0.06
    esian
    0.06
     unsure
    0.06
    ouri
    0.06
    von
    0.06
    bes
    0.05
    arem
    0.05
     chips
    0.05
    Activations Density 0.000%

    No Known Activations