© 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. 55905
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to obtaining or using items

    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
    Äįer
    -0.08
    cek
    -0.07
    δή
    -0.07
    jak
    -0.06
     oppon
    -0.06
    /to
    -0.06
    Enumer
    -0.06
    auty
    -0.06
    ccione
    -0.06
    amas
    -0.06
    POSITIVE LOGITS
     two
    0.08
     several
    0.07
     some
    0.07
    ãģ°ãģĭãĤĬ
    0.07
     this
    0.07
     three
    0.07
     another
    0.07
    /uploads
    0.06
    omic
    0.06
    æĺ¨
    0.06
    Activations Density 0.047%

    No Known Activations