© 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. 83039
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific German words

    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
    furt
    -0.07
    olk
    -0.06
    .ct
    -0.06
    obble
    -0.06
    lek
    -0.06
    олод
    -0.06
    osl
    -0.06
    ému
    -0.06
    ibri
    -0.06
    .Companion
    -0.06
    POSITIVE LOGITS
     फर
    0.06
    ÑĮко
    0.06
    mes
    0.06
     dying
    0.06
    ãĤ¥
    0.06
     discontin
    0.06
    Tooltip
    0.06
    aten
    0.06
    ees
    0.06
     |-
    0.05
    Activations Density 0.000%

    No Known Activations