© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5626
    Prev
    Next
    INDEX
    Explanations

    concepts related to knowledge and understanding

    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
    illas
    -0.07
    ilege
    -0.07
    -strip
    -0.07
     bun
    -0.07
    udies
    -0.06
    ikal
    -0.06
    ovie
    -0.06
    Ñħо
    -0.06
    Verb
    -0.06
     according
    -0.06
    POSITIVE LOGITS
     exact
    0.10
    exact
    0.08
     biết
    0.07
    Exact
    0.07
     whereabouts
    0.07
     knew
    0.07
     precise
    0.07
    æĻĵ
    0.07
     Exact
    0.07
     know
    0.06
    Activations Density 0.027%

    No Known Activations