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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61947
    Prev
    Next
    INDEX
    Explanations

    recurring themes and motifs in narratives

    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
    ħn
    -0.07
    ron
    -0.07
    horn
    -0.07
     seedu
    -0.07
    çĬ¯
    -0.07
    ãĥ£
    -0.06
    ibs
    -0.06
     Yuk
    -0.06
     fron
    -0.06
    tle
    -0.06
    POSITIVE LOGITS
     topics
    0.07
    topic
    0.06
     topic
    0.06
     themes
    0.06
     theme
    0.06
    ît
    0.06
    stice
    0.06
     Topic
    0.06
    izza
    0.06
    inue
    0.06
    Activations Density 0.016%

    No Known Activations