© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88351
    Prev
    Next
    INDEX
    Explanations

    references to local entities and communities

    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
    ORY
    -0.07
    orous
    -0.07
    agger
    -0.07
    ç§į
    -0.07
    JR
    -0.07
    eson
    -0.07
    idel
    -0.07
    asure
    -0.07
    fully
    -0.07
    icial
    -0.06
    POSITIVE LOGITS
    /local
    0.16
    ised
    0.14
    ities
    0.13
    -local
    0.12
    /global
    0.11
    vore
    0.11
    isation
    0.11
    ized
    0.10
    -global
    0.10
    (local
    0.10
    Activations Density 0.036%

    No Known Activations