© 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. 107289
    Prev
    Next
    INDEX
    Explanations

    code and instructions related to application configuration and file management

    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
    adelphia
    -0.07
     Built
    -0.06
     Fork
    -0.06
     disp
    -0.06
     Standards
    -0.06
    ëŀĮ
    -0.06
     Progressive
    -0.06
    XHR
    -0.06
    anager
    -0.06
     earth
    -0.06
    POSITIVE LOGITS
    adro
    0.08
    unma
    0.08
    .dsl
    0.08
     ubic
    0.07
     putas
    0.07
    [src
    0.07
    raÄį
    0.07
    744
    0.07
     ~/.
    0.07
    _periods
    0.07
    Activations Density 0.022%

    No Known Activations