© 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. 130271
    Prev
    Next
    INDEX
    Explanations

    the word "pod" in various forms and 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
    ptal
    -0.07
    byss
    -0.07
    urgeon
    -0.07
    stakes
    -0.06
    vely
    -0.06
     ABI
    -0.06
    بة
    -0.06
    exus
    -0.06
    /lic
    -0.06
    udic
    -0.06
    POSITIVE LOGITS
    neath
    0.09
    lings
    0.08
     conditions
    0.08
    foot
    0.08
     guise
    0.07
     heading
    0.07
    develop
    0.07
     ausp
    0.07
    lie
    0.07
    kin
    0.07
    Activations Density 0.003%

    No Known Activations