© 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. 84022
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational policies and strategies

    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
    raud
    -0.07
    hetto
    -0.06
    ocene
    -0.06
    ull
    -0.06
    ickey
    -0.06
    bid
    -0.06
    меÑĢ
    -0.06
     effic
    -0.06
     Dash
    -0.06
    subcategory
    -0.06
    POSITIVE LOGITS
     approach
    0.13
     Approach
    0.11
     approached
    0.10
     approaching
    0.10
    appro
    0.09
     approaches
    0.09
    Appro
    0.09
    _appro
    0.08
     Appro
    0.07
    ÑģÑĭлки
    0.07
    Activations Density 0.021%

    No Known Activations