© 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. 5-LLAMASCOPE-RES-131K
    11. 125877
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups in the text

    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
     Ding
    -0.06
    Rs
    -0.06
    rail
    -0.05
     pig
    -0.05
    aines
    -0.05
    оваÑĢ
    -0.05
     objectForKey
    -0.05
    cour
    -0.05
    itas
    -0.05
    _MACRO
    -0.05
    POSITIVE LOGITS
    hurst
    0.07
    plets
    0.07
    ordes
    0.07
    нÑıÑĤ
    0.07
    utz
    0.07
    ÙĪÙĨد
    0.06
    ilda
    0.06
    озем
    0.06
    ruž
    0.06
    811
    0.06
    Activations Density 0.042%

    No Known Activations