© 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. 2389
    Prev
    Next
    INDEX
    Explanations

    technical issues related to web browsers, proxies, and software configurations

    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
     Bender
    -0.07
    ведиÑĤе
    -0.07
     ::=
    -0.07
     dobr
    -0.07
     âĸ³
    -0.07
    ofire
    -0.07
     اÙĦÙĬÙĪÙħ
    -0.07
    )["
    -0.07
    retty
    -0.07
     Kürt
    -0.07
    POSITIVE LOGITS
     somehow
    0.17
     somewhere
    0.12
     something
    0.11
     maybe
    0.10
     Somehow
    0.10
    something
    0.09
     perhaps
    0.09
     somew
    0.08
     Something
    0.08
    maybe
    0.07
    Activations Density 0.012%

    No Known Activations