© 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. 125884
    Prev
    Next
    INDEX
    Explanations

    quantifying terms and their frequency within a given context

    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
    ÙĨÚ¯ÛĮ
    -0.07
    vertime
    -0.07
    iegel
    -0.07
    екÑĤоÑĢ
    -0.07
    tal
    -0.07
    iry
    -0.07
    etime
    -0.06
    ãĥ³ãĤ°ãĥ«
    -0.06
    inkel
    -0.06
    .XML
    -0.06
    POSITIVE LOGITS
    haf
    0.06
    dia
    0.06
     Wolff
    0.06
    illos
    0.06
     somehow
    0.06
    .gc
    0.06
    oming
    0.05
     versions
    0.05
    žil
    0.05
     hectares
    0.05
    Activations Density 0.001%

    No Known Activations