© 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. 28683
    Prev
    Next
    INDEX
    Explanations

    titles and references to TV series

    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
    ìĦľëĬĶ
    -0.08
    ãģĬãĤĬ
    -0.08
    ìĦľ
    -0.07
    ansson
    -0.07
    cha
    -0.07
    agers
    -0.07
     slee
    -0.07
    ym
    -0.07
    chl
    -0.07
    ERS
    -0.07
    POSITIVE LOGITS
    icals
    0.08
    bz
    0.08
    ical
    0.07
    AFX
    0.07
    minus
    0.07
    osate
    0.07
    -wide
    0.07
    diet
    0.06
    ive
    0.06
    ANDARD
    0.06
    Activations Density 0.028%

    No Known Activations