© 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. 9-LLAMASCOPE-RES-131K
    11. 95242
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and community support in various contexts

    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
    ermann
    -0.07
    ÐĴÐŀ
    -0.07
    anan
    -0.07
    FRING
    -0.07
    inan
    -0.07
    ÅŁk
    -0.07
    rieb
    -0.07
     Warrior
    -0.07
     Soft
    -0.06
    ouve
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤ°
    0.06
    ually
    0.06
    stad
    0.06
     Hayden
    0.05
     Ñģами
    0.05
    aging
    0.05
    gress
    0.05
    _coef
    0.05
     bath
    0.05
     Ones
    0.05
    Activations Density 0.083%

    No Known Activations