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

    Neuronpedia

    Jacobian LensNEW
    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. 106532
    Prev
    Next
    INDEX
    Explanations

    specific names, terms, or designations related to organizations and their functions

    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
    isté
    -0.07
     disap
    -0.07
    lý
    -0.06
    Ìģt
    -0.06
    IFA
    -0.06
     breat
    -0.06
    idlo
    -0.06
    interesting
    -0.06
    amble
    -0.06
    untu
    -0.06
    POSITIVE LOGITS
    ensex
    0.08
    hus
    0.07
    CESS
    0.07
    ograf
    0.07
    ì¦Ī
    0.07
    ÑĢоÑĪ
    0.07
     Ekon
    0.06
    ÙĩÙĩ
    0.06
    ाà¤Ĺत
    0.06
    ontent
    0.06
    Activations Density 0.631%

    No Known Activations