© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    references to epic stories or narratives in literature

    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
    estar
    -0.07
    tle
    -0.07
     Kraj
    -0.07
    alia
    -0.06
    agen
    -0.06
    ties
    -0.06
    tur
    -0.06
    bridge
    -0.06
    thing
    -0.06
    alet
    -0.06
    POSITIVE LOGITS
    entre
    0.11
    enter
    0.10
    -length
    0.10
    ALLY
    0.09
     proportions
    0.08
    urious
    0.08
    ure
    0.08
    ulously
    0.08
    RIX
    0.07
    çĦ¶
    0.07
    Activations Density 0.005%

    No Known Activations