© 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. 55849
    Prev
    Next
    INDEX
    Explanations

    variations of the word "pok," likely indicating some form of the word "poc" or related terms

    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
    enko
    -0.08
    enia
    -0.08
     seedu
    -0.08
     Rena
    -0.08
    گاÙĨÛĮ
    -0.08
     Infinite
    -0.08
    FINITE
    -0.07
    FTWARE
    -0.07
    RIEND
    -0.07
    mada
    -0.07
    POSITIVE LOGITS
    ht
    0.08
    etch
    0.08
     flip
    0.07
    vor
    0.07
     fair
    0.07
    rip
    0.07
    istani
    0.06
    kin
    0.06
    flip
    0.06
    cem
    0.06
    Activations Density 0.006%

    No Known Activations