© 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. 78091
    Prev
    Next
    INDEX
    Explanations

    compound words or hyphenated terms related to positions or roles

    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
    ellido
    -0.07
    è¾ŀ
    -0.07
     ActiveForm
    -0.07
    [".
    -0.07
     çĻ¾
    -0.06
    etur
    -0.06
    -ÑĤо
    -0.06
    á»ķ
    -0.06
    .createComponent
    -0.06
    cona
    -0.06
    POSITIVE LOGITS
    -basic
    0.07
    Calibri
    0.06
    \'
    0.06
     basic
    0.06
     basics
    0.06
     Ùħبت
    0.06
     indem
    0.06
    dea
    0.06
    \:
    0.06
     \'
    0.06
    Activations Density 0.000%

    No Known Activations