© 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. 128809
    Prev
    Next
    INDEX
    Explanations

    the word "Throughout" and related patterns indicating continuity or recurring themes

    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
    ungi
    -0.06
    ucken
    -0.06
    agrams
    -0.06
    sect
    -0.06
    hor
    -0.06
    ensed
    -0.06
    ilia
    -0.06
    scape
    -0.06
    ridged
    -0.06
    lear
    -0.05
    POSITIVE LOGITS
     throughout
    0.09
     Throughout
    0.08
    Throughout
    0.07
     history
    0.07
    engo
    0.07
     Geschichte
    0.07
    ongo
    0.06
    å¡ļ
    0.06
    æĢ§çļĦ
    0.06
    _placeholder
    0.06
    Activations Density 0.006%

    No Known Activations