© 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. 83766
    Prev
    Next
    INDEX
    Explanations

    the name "Janet", likely in the context of various narratives or texts

    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
    sy
    -0.08
    ennon
    -0.07
    san
    -0.07
    slot
    -0.07
    service
    -0.07
    бÑĥ
    -0.07
    sWith
    -0.07
    ogan
    -0.07
     Closure
    -0.07
    uko
    -0.07
    POSITIVE LOGITS
    ted
    0.10
    tml
    0.08
    ta
    0.07
    amel
    0.07
    undry
    0.07
    ously
    0.07
    ajs
    0.07
     pus
    0.07
    ting
    0.06
    rypt
    0.06
    Activations Density 0.008%

    No Known Activations