© 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. 40255
    Prev
    Next
    INDEX
    Explanations

    actions or processes related to business operations and logistics

    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
    łĢ
    -0.07
    acker
    -0.07
    igua
    -0.07
    iets
    -0.06
    ãĥªãĥ¼
    -0.06
    enco
    -0.06
    ughter
    -0.06
    rium
    -0.06
    DEX
    -0.06
    го
    -0.06
    POSITIVE LOGITS
     thr
    0.07
     exact
    0.07
    ewis
    0.07
    GGLE
    0.07
     them
    0.06
    fcc
    0.06
     puss
    0.06
    PÅĻi
    0.06
    iate
    0.06
    ccb
    0.06
    Activations Density 0.148%

    No Known Activations