© 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. 54829
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers related to products and programs

    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
    missions
    -0.08
    iku
    -0.07
     colon
    -0.07
    angelo
    -0.07
    ummer
    -0.07
    ="{!!
    -0.06
    ajar
    -0.06
    Exc
    -0.06
    OperationException
    -0.06
    è¯
    -0.06
    POSITIVE LOGITS
     ref
    0.06
    ãģıãģł
    0.06
     number
    0.06
     Morav
    0.06
     Hack
    0.06
    ynchron
    0.06
    aten
    0.05
     Bend
    0.05
     mov
    0.05
     paci
    0.05
    Activations Density 0.065%

    No Known Activations