© 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. 15-LLAMASCOPE-RES-131K
    11. 26388
    Prev
    Next
    INDEX
    Explanations

    questions and aspects related to email marketing, particularly around spam complaints and deliverability issues

    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
    esen
    -0.07
    zcze
    -0.07
    osti
    -0.06
    ATUS
    -0.06
    itchens
    -0.06
    .Mapping
    -0.06
    HEST
    -0.06
    iyim
    -0.06
    ģµ
    -0.06
    nim
    -0.06
    POSITIVE LOGITS
     measures
    0.07
    èį£
    0.06
    Paginator
    0.06
     Measures
    0.06
    dock
    0.06
    окол
    0.06
    /Image
    0.06
    olean
    0.06
    healthy
    0.06
    urtles
    0.06
    Activations Density 0.004%

    No Known Activations