© 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. 79921
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with communication technology and system functionalities

    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
     libertin
    -0.08
    511
    -0.07
    radient
    -0.07
    allon
    -0.07
    dre
    -0.07
    lue
    -0.07
    اÙĪÙĬØ©
    -0.07
    empo
    -0.07
    /Table
    -0.07
    velte
    -0.07
    POSITIVE LOGITS
     option
    0.11
     optionally
    0.08
     facility
    0.08
     possibility
    0.08
    option
    0.08
     capability
    0.08
     Option
    0.07
     Möglichkeit
    0.07
     mode
    0.07
     incl
    0.07
    Activations Density 0.031%

    No Known Activations