© 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. 61105
    Prev
    Next
    INDEX
    Explanations

    significant quantifiers or descriptors indicating levels and standards

    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
    âĢ¦↵
    -0.08
     [âĢ¦]↵
    -0.07
     only
    -0.07
     instead
    -0.07
     âĢ¦↵
    -0.07
    âĢ¦
    -0.07
     and
    -0.06
     solely
    -0.06
     [âĢ¦]
    -0.06
    instead
    -0.06
    POSITIVE LOGITS
     -*-č↵
    0.08
    etti
    0.08
    ÐĶÐļ
    0.07
    ocale
    0.07
     pozor
    0.07
     ÑĪÑĤÑĥ
    0.07
     tremend
    0.07
     má»
    0.07
    (Of
    0.07
    çĹ
    0.07
    Activations Density 0.011%

    No Known Activations