© 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. 86655
    Prev
    Next
    INDEX
    Explanations

    references to clients or customers

    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
    éĹ»
    -0.07
    oph
    -0.07
    ippo
    -0.06
     Blanc
    -0.06
     Sax
    -0.06
     Scene
    -0.06
    ois
    -0.06
    obs
    -0.06
     cosine
    -0.06
    (Seq
    -0.06
    POSITIVE LOGITS
    ONUS
    0.07
    üle
    0.07
    CastException
    0.07
    층
    0.06
    uzzer
    0.06
    ullah
    0.06
    ltk
    0.06
     feedback
    0.06
    370
    0.06
    导
    0.06
    Activations Density 0.044%

    No Known Activations