© 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. 125038
    Prev
    Next
    INDEX
    Explanations

    references to events or publications related to various media

    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
     Bert
    -0.06
    izar
    -0.06
    iken
    -0.06
     Tek
    -0.06
    omedical
    -0.06
    163
    -0.06
    ujet
    -0.06
    773
    -0.05
     sept
    -0.05
    vincia
    -0.05
    POSITIVE LOGITS
    bases
    0.07
    าะ
    0.07
    è²
    0.07
    rowning
    0.07
    ees
    0.07
    ÑĤÑİ
    0.06
    kaz
    0.06
    \uc
    0.06
    ее
    0.06
    yer
    0.06
    Activations Density 0.103%

    No Known Activations