© 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 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. 17-LLAMASCOPE-RES-131K
    11. 56005
    Prev
    Next
    INDEX
    Explanations

    references to sponge iron and related processes

    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
    xis
    -0.08
    aclass
    -0.07
     è§
    -0.07
    sik
    -0.06
    anax
    -0.06
    quil
    -0.06
    ambre
    -0.06
    ubes
    -0.06
    mong
    -0.06
    cribed
    -0.06
    POSITIVE LOGITS
    y
    0.08
    ular
    0.07
    fy
    0.07
    oidal
    0.07
    allax
    0.07
    ÅĻeb
    0.07
    æĭ¬
    0.07
    gebn
    0.07
    blank
    0.07
    ptive
    0.07
    Activations Density 0.006%

    No Known Activations