© 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. 94957
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Iron" in various contexts

    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
    uries
    -0.07
    JE
    -0.06
    gt
    -0.06
    led
    -0.06
     Cummings
    -0.06
    lar
    -0.06
    _UNS
    -0.06
     Hoy
    -0.06
    agr
    -0.06
    apers
    -0.06
    POSITIVE LOGITS
    mong
    0.07
     deficiency
    0.07
     oxide
    0.07
    нод
    0.07
    ically
    0.07
     supplement
    0.07
     ore
    0.07
    ród
    0.07
    works
    0.07
    ilde
    0.07
    Activations Density 0.008%

    No Known Activations