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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106891
    Prev
    Next
    INDEX
    Explanations

    references to time durations and numerical data related to years and financial amounts

    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
    gado
    -0.07
    enet
    -0.07
    VO
    -0.07
    #echo
    -0.07
    меÑĢ
    -0.06
     bilg
    -0.06
    _frontend
    -0.06
    beb
    -0.06
    chant
    -0.06
    geh
    -0.06
    POSITIVE LOGITS
     etc
    0.09
    çĶļèĩ³
    0.07
    etc
    0.07
     or
    0.07
     depending
    0.06
    微软éĽħé»ij
    0.06
    depending
    0.06
     depends
    0.06
    ults
    0.06
     sogar
    0.06
    Activations Density 0.020%

    No Known Activations