© 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. 116916
    Prev
    Next
    INDEX
    Explanations

    references to structural concepts 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
    dra
    -0.08
    ãģĬãĤĬ
    -0.08
    isen
    -0.08
    ãĤ©
    -0.08
    ossible
    -0.07
    å¸ģ
    -0.07
    ê
    -0.07
    è¼
    -0.07
    ameda
    -0.07
    ÌĢ
    -0.07
    POSITIVE LOGITS
    urally
    0.10
     timeval
    0.10
    ively
    0.09
    alist
    0.09
    ivist
    0.07
    less
    0.07
    tte
    0.07
    ophil
    0.07
    ural
    0.07
    lle
    0.07
    Activations Density 0.029%

    No Known Activations