© 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. 55515
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and journals

    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
     Ru
    -0.06
    baugh
    -0.06
    Entries
    -0.06
    Ì
    -0.06
    -La
    -0.05
     Entries
    -0.05
    askell
    -0.05
     pend
    -0.05
    Vars
    -0.05
    bank
    -0.05
    POSITIVE LOGITS
    AMED
    0.07
    brtc
    0.07
    PURE
    0.07
    hdl
    0.07
    edor
    0.07
    寸
    0.07
    eken
    0.07
    IGHL
    0.07
    ezier
    0.07
    ekk
    0.07
    Activations Density 0.003%

    No Known Activations