© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or analytical concepts and their applications

    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
    ÏĩεδÏĮν
    -0.08
    zing
    -0.07
    XS
    -0.07
    arih
    -0.07
    Ïģκε
    -0.07
    allet
    -0.06
    nero
    -0.06
     voksen
    -0.06
    oice
    -0.06
    ismet
    -0.06
    POSITIVE LOGITS
     than
    0.32
    than
    0.27
     THAN
    0.25
    -than
    0.25
     Than
    0.24
    _than
    0.23
    Than
    0.23
     niż
    0.19
     než
    0.18
     än
    0.16
    Activations Density 0.121%

    No Known Activations