© 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. 126481
    Prev
    Next
    INDEX
    Explanations

    concepts related to the idea of persistence or continuity

    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
    athan
    -0.09
    er
    -0.07
    -ÑĤо
    -0.07
    Reuse
    -0.07
    erie
    -0.07
    /tiny
    -0.06
    ابت
    -0.06
    erule
    -0.06
    skip
    -0.06
     costa
    -0.06
    POSITIVE LOGITS
    ently
    0.13
    ency
    0.09
    ence
    0.08
    /rec
    0.07
    icone
    0.07
    ences
    0.07
    uner
    0.07
    ment
    0.07
    ously
    0.07
    aye
    0.06
    Activations Density 0.004%

    No Known Activations