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

    Neuronpedia

    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. 4362
    Prev
    Next
    INDEX
    Explanations

    conditional phrases starting with "if."

    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
    icens
    -0.08
    ван
    -0.07
    ylon
    -0.07
    аÑĪа
    -0.07
    ä¸įäºĨ
    -0.07
     Kraj
    -0.07
    ores
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
     _______,
    -0.07
    stad
    -0.06
    POSITIVE LOGITS
    /how
    0.15
     there
    0.10
     they
    0.07
     it
    0.07
     INCIDENT
    0.07
    there
    0.07
    uda
    0.06
     any
    0.06
    бол
    0.06
    hc
    0.06
    Activations Density 0.015%

    No Known Activations