© 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 EvalsExportsinterp-engineNEWAPI 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. 62626
    Prev
    Next
    INDEX
    Explanations

    elements related to file input and output operations in programming code

    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
     Fol
    -0.06
    edla
    -0.06
    495
    -0.06
     Gre
    -0.06
    otr
    -0.06
     boarding
    -0.05
    led
    -0.05
     Reid
    -0.05
    urations
    -0.05
     Stock
    -0.05
    POSITIVE LOGITS
    babel
    0.07
     Animalia
    0.07
    planet
    0.07
    çĪ½
    0.07
    orian
    0.07
    diet
    0.07
    orsi
    0.07
    Lifetime
    0.06
    sik
    0.06
    _mgmt
    0.06
    Activations Density 0.031%

    No Known Activations