© 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. 79141
    Prev
    Next
    INDEX
    Explanations

    structured information related to film and media details

    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
    erala
    -0.06
    805
    -0.06
    awa
    -0.06
    asted
    -0.06
    esimal
    -0.06
    outs
    -0.06
    als
    -0.06
    olla
    -0.05
     widest
    -0.05
     Outs
    -0.05
    POSITIVE LOGITS
    #ad
    0.09
    Forgery
    0.09
    erli
    0.08
    FOUNDATION
    0.08
    linger
    0.07
    ạp
    0.07
    _budget
    0.07
    à¸Ńà¸ĩ
    0.07
    iddet
    0.07
    ãģĹãĤĩãģĨ
    0.07
    Activations Density 0.008%

    No Known Activations