© 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. 15-LLAMASCOPE-RES-131K
    11. 713
    Prev
    Next
    INDEX
    Explanations

    specific names or potentially proper nouns within a text

    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
    oli
    -0.07
    acre
    -0.06
     dot
    -0.06
     Tos
    -0.06
     Sn
    -0.06
    ãĥģãĥ¥
    -0.06
    576
    -0.06
    rie
    -0.06
    rek
    -0.06
     Lac
    -0.06
    POSITIVE LOGITS
    .gstatic
    0.08
    Ľå»º
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    onavir
    0.07
    OutOfRangeException
    0.07
    .scalablytyped
    0.07
    _exempt
    0.07
    IIIK
    0.07
    à¸IJ
    0.07
     realized
    0.07
    Activations Density 0.017%

    No Known Activations