© 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. 41965
    Prev
    Next
    INDEX
    Explanations

    phrases indicating novelty or significance in contexts

    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
    alse
    -0.06
     defaultManager
    -0.06
    AMI
    -0.06
    orate
    -0.06
    erg
    -0.06
     gó
    -0.06
    nst
    -0.06
    nth
    -0.06
    ợ
    -0.06
    nten
    -0.06
    POSITIVE LOGITS
     interesting
    0.08
     new
    0.08
     recently
    0.08
    edis
    0.07
    new
    0.07
     derec
    0.07
     phenomenon
    0.07
    haps
    0.07
    ÑıÑĤ
    0.07
     phenomena
    0.07
    Activations Density 0.027%

    No Known Activations