© 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. 78255
    Prev
    Next
    INDEX
    Explanations

    specific company and product names in various contexts

    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
    %C
    -0.08
    /or
    -0.07
     or
    -0.07
     other
    -0.07
    styleType
    -0.06
    ovit
    -0.06
    Ìģt
    -0.06
     aforementioned
    -0.06
    olet
    -0.06
    orra
    -0.06
    POSITIVE LOGITS
    .mousePosition
    0.07
    änder
    0.07
     còn
    0.07
    AUSE
    0.07
    çok
    0.07
    Leaks
    0.07
     éĬ
    0.07
    asu
    0.07
    eel
    0.07
    ÏģÏĮ
    0.07
    Activations Density 0.040%

    No Known Activations