© 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. 125763
    Prev
    Next
    INDEX
    Explanations

    present continuous phrases indicating ongoing actions or states

    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
    _contin
    -0.07
    olumn
    -0.07
    chas
    -0.06
    .toHexString
    -0.06
     alum
    -0.06
    locker
    -0.06
    rikes
    -0.06
    à¥Ģà¤Ĺ
    -0.06
    ijn
    -0.05
    ental
    -0.05
    POSITIVE LOGITS
    enan
    0.07
    ayette
    0.07
    aines
    0.06
    aina
    0.06
    enko
    0.06
     Lifestyle
    0.06
    ostel
    0.06
     pads
    0.06
    zy
    0.06
    ?a
    0.06
    Activations Density 0.014%

    No Known Activations