© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119796
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling and narrative structure

    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
    ani
    -0.08
    insky
    -0.07
    angle
    -0.07
    è§Ĵ
    -0.07
    abbo
    -0.07
    inati
    -0.07
    engin
    -0.07
    åĩºãģĹ
    -0.07
    ÑĢÑĸÑĪ
    -0.07
    .Networking
    -0.07
    POSITIVE LOGITS
     intermediate
    0.17
     intervening
    0.17
     Intermediate
    0.15
    Intermediate
    0.13
     intermedi
    0.13
     intermediary
    0.13
     interim
    0.12
     between
    0.12
     Between
    0.11
     middle
    0.11
    Activations Density 0.048%

    No Known Activations