© 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 EvalsExportsinterp-engineNEWAPI 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. 117869
    Prev
    Next
    INDEX
    Explanations

    references to "Old" followed by various terms related to age or history

    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
    undles
    -0.07
    ected
    -0.07
    iland
    -0.07
    oras
    -0.06
    789
    -0.06
    etics
    -0.06
    _SECURE
    -0.06
    ÙĪئ
    -0.06
    ollapse
    -0.06
    dia
    -0.06
    POSITIVE LOGITS
    -fashioned
    0.17
     fashioned
    0.15
    /new
    0.12
    /New
    0.11
    -school
    0.10
    ÅĻich
    0.10
    enburg
    0.10
    timer
    0.09
    -fashion
    0.09
    school
    0.09
    Activations Density 0.037%

    No Known Activations