© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1158
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their relationships in theoretical discussions

    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
    et
    -0.06
     ama
    -0.06
    assi
    -0.06
    宾
    -0.06
    conc
    -0.05
    115
    -0.05
    éo
    -0.05
     conventional
    -0.05
    acey
    -0.05
     "
    -0.05
    POSITIVE LOGITS
    extensions
    0.09
    -extension
    0.09
    Extension
    0.09
     Extension
    0.08
    Extensions
    0.08
    extension
    0.08
    _extensions
    0.08
    _EXTENSIONS
    0.08
     extension
    0.08
    Handling
    0.07
    Activations Density 0.042%

    No Known Activations