© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77853
    Prev
    Next
    INDEX
    Explanations

    variations of the word "represent" and its derivatives

    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
    rane
    -0.07
    ickness
    -0.07
    esium
    -0.07
     kou
    -0.06
     âĹĦ
    -0.06
    eras
    -0.06
    uality
    -0.06
    osate
    -0.06
    éĺħ读次æķ°
    -0.06
    üss
    -0.06
    POSITIVE LOGITS
     representation
    0.09
     Representation
    0.09
     represent
    0.08
     Ñģобой
    0.08
    ational
    0.08
     representing
    0.07
    rzy
    0.07
    atively
    0.07
    representation
    0.07
    ative
    0.07
    Activations Density 0.011%

    No Known Activations