© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88568
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their statements or actions

    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
     memor
    -0.07
    etc
    -0.06
    fi
    -0.06
    823
    -0.06
    hled
    -0.05
    000
    -0.05
     yếu
    -0.05
     Coun
    -0.05
    LOUD
    -0.05
    pl
    -0.05
    POSITIVE LOGITS
    olars
    0.07
    ÅĻes
    0.07
     explanation
    0.07
    ë¶
    0.07
    éĽ»è©±
    0.07
    tesy
    0.07
    _relu
    0.07
     explain
    0.07
    osit
    0.07
     explained
    0.06
    Activations Density 0.029%

    No Known Activations