© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127393
    Prev
    Next
    INDEX
    Explanations

    references to the brand or entity "MB" and its derivatives in various 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
    oi
    -0.09
    edn
    -0.09
    luv
    -0.08
    ois
    -0.08
    utenberg
    -0.08
    oad
    -0.07
    oze
    -0.07
    ErrMsg
    -0.07
    oon
    -0.07
    itar
    -0.07
    POSITIVE LOGITS
    oko
    0.07
    imet
    0.06
    im
    0.06
    rie
    0.06
     Malik
    0.06
    <decltype
    0.06
     Willi
    0.06
    hab
    0.06
    alat
    0.06
    amel
    0.06
    Activations Density 0.028%

    No Known Activations