© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87255
    Prev
    Next
    INDEX
    Explanations

    elements related to web feeds and hyperlinks

    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
    -Ñħ
    -0.06
    çłĶç©¶æīĢ
    -0.06
    nou
    -0.06
    ryption
    -0.06
     Anthem
    -0.06
     ذ
    -0.06
    aidu
    -0.06
    Alive
    -0.05
    eno
    -0.05
    reff
    -0.05
    POSITIVE LOGITS
    onical
    0.07
     feeds
    0.07
    #error
    0.07
     subscribe
    0.07
    -feed
    0.07
     Všech
    0.07
    iyon
    0.07
     aks
    0.07
    yme
    0.07
     Mast
    0.07
    Activations Density 0.001%

    No Known Activations