© 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. 3363
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods and financial references related to monthly and quarterly metrics

    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
    ridden
    -0.07
    hrad
    -0.07
    idot
    -0.07
    aday
    -0.06
    нÑĥÑĤ
    -0.06
    istrator
    -0.06
    IME
    -0.06
     cocos
    -0.06
    ime
    -0.06
    imony
    -0.06
    POSITIVE LOGITS
    izr
    0.07
    anton
    0.07
     faces
    0.07
    Faces
    0.07
    CHIP
    0.06
     Faces
    0.06
     dim
    0.06
     Econ
    0.06
    lyn
    0.06
    CDATA
    0.06
    Activations Density 0.004%

    No Known Activations