© 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. 121254
    Prev
    Next
    INDEX
    Explanations

    elements related to language structure and word formation

    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
    erg
    -0.07
    Marker
    -0.06
    MF
    -0.06
     comma
    -0.06
    dated
    -0.06
    quarter
    -0.06
     shorthand
    -0.06
    Stripe
    -0.06
     Marker
    -0.06
    æĶ¯
    -0.06
    POSITIVE LOGITS
     letters
    0.08
     phon
    0.07
    pun
    0.07
     word
    0.07
     pun
    0.07
     пеÑĢеÑģÑĤ
    0.07
     letter
    0.07
     gem
    0.07
     inversion
    0.07
     formations
    0.06
    Activations Density 0.080%

    No Known Activations