© 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. 17-LLAMASCOPE-RES-131K
    11. 60784
    Prev
    Next
    INDEX
    Explanations

    phrases indicating locations or contexts within the film narrative

    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
     eldre
    -0.06
    fter
    -0.06
    entine
    -0.06
    ansi
    -0.06
     sed
    -0.06
    ÃŃky
    -0.06
     Newman
    -0.06
    æİī
    -0.06
     Dew
    -0.06
    ãģ¨ãģĵãĤį
    -0.05
    POSITIVE LOGITS
     this
    0.09
    ↵↵
    0.07
    illance
    0.07
    orce
    0.07
    this
    0.07
    ograd
    0.07
    ocene
    0.07
    该
    0.06
    iland
    0.06
    book
    0.06
    Activations Density 0.024%

    No Known Activations