© 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. 78851
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data management and analytics

    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
    коз
    -0.08
    ignum
    -0.08
    gers
    -0.07
    /MPL
    -0.07
    icode
    -0.07
    ãĥĨãĥ«
    -0.07
     kì
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    ινÏĮ
    -0.07
    enÃŃ
    -0.07
    POSITIVE LOGITS
    -like
    0.08
    -based
    0.08
    -type
    0.07
    -style
    0.07
     approach
    0.07
    -Based
    0.07
     principle
    0.06
     applied
    0.06
    977
    0.06
     concept
    0.06
    Activations Density 0.084%

    No Known Activations