© 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. 29044
    Prev
    Next
    INDEX
    Explanations

    references to the Internet of Things (IoT)

    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
    -0.06
     Rise
    -0.06
    nett
    -0.06
    unct
    -0.06
    ross
    -0.06
    avid
    -0.06
    uest
    -0.05
    oci
    -0.05
    itsu
    -0.05
    alf
    -0.05
    POSITIVE LOGITS
    STITUTE
    0.07
    .promise
    0.07
    rex
    0.07
    Ñīа
    0.07
     baģlı
    0.07
    achs
    0.07
     плиÑĤ
    0.07
    zac
    0.06
    osu
    0.06
    +xml
    0.06
    Activations Density 0.001%

    No Known Activations