© 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. 15-LLAMASCOPE-RES-131K
    11. 27024
    Prev
    Next
    INDEX
    Explanations

    financial reporting metrics and periods

    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
    wright
    -0.07
     Lun
    -0.07
    nick
    -0.07
    stoff
    -0.06
     glasses
    -0.06
     Hud
    -0.06
    entiful
    -0.06
    ILLE
    -0.06
     average
    -0.06
     Mach
    -0.06
    POSITIVE LOGITS
    ÏĥοÏħ
    0.07
    ãĥĶãĥ¼
    0.07
    _portal
    0.06
     kep
    0.06
    558
    0.06
    liner
    0.06
     operands
    0.06
    /Peak
    0.06
    à¸Ńà¸Ķ
    0.06
    [Test
    0.06
    Activations Density 0.007%

    No Known Activations