Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29031
    Prev
    Next
    INDEX
    Explanations

    closing brackets and semicolons in code

    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
     подв
    -0.07
    chwitz
    -0.07
    CLUDED
    -0.07
    PLUGIN
    -0.07
    ÙĪÙĤ
    -0.07
    anoia
    -0.07
    xac
    -0.07
    omor
    -0.07
    teri
    -0.07
    η
    -0.07
    POSITIVE LOGITS
    ock
    0.07
    729
    0.06
     
    0.06
     Plum
    0.05
    CTest
    0.05
     eslint
    0.05
    awai
    0.05
     ex
    0.05
    ,
    0.05
     Kostenlos
    0.05
    Activations Density 0.005%

    No Known Activations