© 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. 72023
    Prev
    Next
    INDEX
    Explanations

    significant nouns and their relationship to themes of storytelling and narrative exploration

    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
    онÑĮ
    -0.09
    (æ°´
    -0.08
    _SS
    -0.08
    FRING
    -0.08
     componentDid
    -0.08
     облиÑĩ
    -0.07
    cour
    -0.07
    ÑģÑİ
    -0.07
    cant
    -0.07
     VÃŃ
    -0.07
    POSITIVE LOGITS
     aspect
    0.09
     aspects
    0.09
     portions
    0.07
    pects
    0.07
     Aspect
    0.07
    aspect
    0.06
     range
    0.06
    éĿ
    0.06
    era
    0.06
     important
    0.06
    Activations Density 0.029%

    No Known Activations