© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56537
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "free" in various contexts, particularly related to licenses or availability

    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
    afort
    -0.07
    landa
    -0.07
    rieve
    -0.07
    ardy
    -0.07
    'gc
    -0.07
    ulen
    -0.06
    reve
    -0.06
    xDE
    -0.06
    VEC
    -0.06
    ilet
    -0.06
    POSITIVE LOGITS
    628
    0.07
     Tato
    0.06
    gage
    0.06
    kre
    0.06
    yntax
    0.06
     Craig
    0.06
    chemas
    0.06
     www
    0.06
    iji
    0.06
     Guys
    0.06
    Activations Density 0.001%

    No Known Activations