© 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. 15-LLAMASCOPE-RES-131K
    11. 90610
    Prev
    Next
    INDEX
    Explanations

    phrases expressing comparisons or proportions

    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
    ifers
    -0.09
    enberg
    -0.07
    važ
    -0.07
    _PK
    -0.07
    atu
    -0.07
    =pk
    -0.07
    #line
    -0.07
    ega
    -0.07
    opp
    -0.07
    adel
    -0.06
    POSITIVE LOGITS
    omor
    0.06
    ihad
    0.06
    nÃŃ
    0.06
    ,
    0.06
    wc
    0.06
    ltra
    0.06
     feedback
    0.05
     on
    0.05
    ë§ī
    0.05
    ames
    0.05
    Activations Density 0.009%

    No Known Activations