© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 59748
    Prev
    Next
    INDEX
    Explanations

    references to community-related content and events

    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
     states
    -0.07
     Kraj
    -0.06
    ůst
    -0.06
    -states
    -0.06
    .Accessible
    -0.06
     estados
    -0.06
    States
    -0.06
     Wales
    -0.06
    ÏĦÏģ
    -0.06
    .ov
    -0.06
    POSITIVE LOGITS
     local
    0.16
     community
    0.14
    local
    0.13
     LOCAL
    0.13
     locally
    0.13
     Local
    0.12
    community
    0.12
    locals
    0.11
    Local
    0.11
     locals
    0.11
    Activations Density 0.022%

    No Known Activations