© 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. 93302
    Prev
    Next
    INDEX
    Explanations

    references to computer protocols and technical specifications related to security and data communications

    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
    vla
    -0.06
    dings
    -0.06
    aben
    -0.06
    setIcon
    -0.06
    evity
    -0.06
    øy
    -0.06
    ecided
    -0.06
    aptor
    -0.06
    tright
    -0.06
    oyo
    -0.06
    POSITIVE LOGITS
    stands
    0.09
    abbreviation
    0.08
     acronym
    0.08
     stands
    0.07
    ä»
    0.06
     abbreviation
    0.06
    VarChar
    0.06
     Hew
    0.06
    acr
    0.06
    ahy
    0.06
    Activations Density 0.040%

    No Known Activations