© 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. 17689
    Prev
    Next
    INDEX
    Explanations

    references to a specific file path or document structure

    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
    rite
    -0.08
    CRET
    -0.08
    GIN
    -0.08
    plen
    -0.08
    essen
    -0.07
    assi
    -0.07
    ampo
    -0.07
    RAIN
    -0.07
    inh
    -0.07
    MOTE
    -0.07
    POSITIVE LOGITS
    abis
    0.06
    sus
    0.06
    oin
    0.06
     Thur
    0.06
    bcm
    0.05
    oris
    0.05
     Randall
    0.05
    BJ
    0.05
    OUR
    0.05
    arge
    0.05
    Activations Density 0.001%

    No Known Activations