© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130391
    Prev
    Next
    INDEX
    Explanations

    significant achievements and milestones in a person's career

    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
    agus
    -0.09
    IMS
    -0.08
    ÐķТ
    -0.08
    οκ
    -0.07
    ramer
    -0.07
    okt
    -0.07
    ould
    -0.07
     Qed
    -0.07
    UiThread
    -0.07
    едÑĮ
    -0.07
    POSITIVE LOGITS
     again
    0.08
     later
    0.06
     vestib
    0.06
     Again
    0.06
    â
    0.06
     subsequent
    0.06
     novamente
    0.06
     carr
    0.06
     subsequently
    0.05
     Primitive
    0.05
    Activations Density 0.090%

    No Known Activations