© 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. 15-LLAMASCOPE-RES-131K
    11. 89627
    Prev
    Next
    INDEX
    Explanations

    terms related to "beam" in various contexts within technical and scientific discussions

    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
    ãģªãģĦ
    -0.07
    ôi
    -0.07
    arpa
    -0.06
    sy
    -0.06
    ëģĶ
    -0.06
    verture
    -0.06
    pard
    -0.06
    pie
    -0.06
     Loose
    -0.06
    /constants
    -0.06
    POSITIVE LOGITS
    forming
    0.08
    idine
    0.07
    Äĥn
    0.07
    ery
    0.07
    ТÐŀ
    0.07
    stalk
    0.07
    oldur
    0.07
    former
    0.07
    lines
    0.07
    749
    0.07
    Activations Density 0.014%

    No Known Activations