© 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. 30554
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the popularity and acclaim of a game or creative work

    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
    ноÑĪ
    -0.06
    ervlet
    -0.06
    prs
    -0.06
    occus
    -0.06
     ÐĿаÑĢод
    -0.06
    UCE
    -0.06
    άνÏī
    -0.06
    uce
    -0.06
    imb
    -0.06
    erap
    -0.06
    POSITIVE LOGITS
     features
    0.07
    features
    0.07
     Permit
    0.07
    å±ŀ
    0.06
    ì§ij
    0.06
    emsp
    0.06
     akci
    0.06
    mouth
    0.06
     @@↵
    0.06
    ythe
    0.06
    Activations Density 0.001%

    No Known Activations