© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86844
    Prev
    Next
    INDEX
    Explanations

    terms related to the effectiveness, efficacy, and legality of concepts or policies

    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
    ogui
    -0.08
    igung
    -0.07
    izzato
    -0.07
    óż
    -0.07
    ucci
    -0.06
    ekler
    -0.06
    ToStr
    -0.06
    zdy
    -0.06
    lessly
    -0.06
    ÏģÏħ
    -0.06
    POSITIVE LOGITS
    iness
    0.08
     extent
    0.07
    extent
    0.07
    оÑģÑĤÑĮ
    0.06
    pecia
    0.06
    otypical
    0.06
    fulness
    0.06
    384
    0.06
    iveness
    0.06
    à¹ĩà¸ķ
    0.06
    Activations Density 0.023%

    No Known Activations