© 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. 93696
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to scientific calculations and formulas

    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
    nger
    -0.08
    ichel
    -0.08
     Sez
    -0.07
    еви
    -0.07
    lun
    -0.07
    rif
    -0.07
    rud
    -0.07
    adge
    -0.07
     jint
    -0.07
    reh
    -0.07
    POSITIVE LOGITS
     sto
    0.11
     chemical
    0.09
     chem
    0.09
     Chem
    0.09
     Chemical
    0.08
    chem
    0.08
     mole
    0.07
    Chem
    0.07
     reaction
    0.07
     chemistry
    0.07
    Activations Density 0.007%

    No Known Activations