© 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. 130842
    Prev
    Next
    INDEX
    Explanations

    references to filters and filtration processes

    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
    nicas
    -0.07
    alborg
    -0.07
    ucer
    -0.07
    lish
    -0.07
    annes
    -0.06
    ร
    -0.06
    els
    -0.06
    _compat
    -0.06
    icast
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
    edReader
    0.10
    edImage
    0.09
    ë§ģ
    0.09
    ting
    0.08
    ation
    0.08
    (ed
    0.08
    able
    0.07
    åĻ¨
    0.07
    515
    0.07
    ered
    0.07
    Activations Density 0.009%

    No Known Activations