© 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. 84145
    Prev
    Next
    INDEX
    Explanations

    specific dates and release information

    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
    ects
    -0.07
    otron
    -0.07
     scen
    -0.06
     Barcl
    -0.06
    ples
    -0.06
    ences
    -0.06
    à¸Ĺร
    -0.06
    еÑĢÑĥ
    -0.06
    ån
    -0.06
     perm
    -0.06
    POSITIVE LOGITS
     Nationwide
    0.07
     worldwide
    0.06
     nationwide
    0.06
     exclusively
    0.06
    orig
    0.06
     preceded
    0.06
    INO
    0.06
    owitz
    0.06
    \Bridge
    0.06
    iversal
    0.06
    Activations Density 0.012%

    No Known Activations