© 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. 27095
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or exclusions

    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
    mlin
    -0.06
    istrat
    -0.06
    eland
    -0.06
    etz
    -0.06
    rus
    -0.06
     Solo
    -0.06
     normalize
    -0.06
     nIndex
    -0.06
     bump
    -0.06
    osu
    -0.05
    POSITIVE LOGITS
    OLON
    0.07
    oload
    0.07
    _usec
    0.07
    адÑĥ
    0.06
    acom
    0.06
    ëĿ¼
    0.06
    OAD
    0.06
     ÑĤÑĸ
    0.06
    raq
    0.06
    iske
    0.06
    Activations Density 0.000%

    No Known Activations