© 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. 129066
    Prev
    Next
    INDEX
    Explanations

    references to career paths and professional experiences

    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
    rouch
    -0.08
    ading
    -0.07
    witter
    -0.07
    ault
    -0.07
    ritten
    -0.07
     Hiro
    -0.07
    chia
    -0.07
    ë²Į
    -0.07
    reich
    -0.06
    ichert
    -0.06
    POSITIVE LOGITS
    lap
    0.06
    ups
    0.06
    409
    0.06
    -scrollbar
    0.06
    430
    0.06
    uple
    0.06
    igung
    0.06
    unic
    0.06
    -long
    0.06
     with
    0.05
    Activations Density 0.005%

    No Known Activations