© 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. 15-LLAMASCOPE-RES-131K
    6. 26397
    Prev
    Next
    INDEX
    Explanations

    mentions of significant changes or decisions in situations

    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
    éĢĨ
    -0.07
     nackte
    -0.07
    ίκη
    -0.06
    iers
    -0.06
    oloj
    -0.06
    .findall
    -0.06
     Nir
    -0.06
    \Collections
    -0.06
    .ids
    -0.06
    flt
    -0.06
    POSITIVE LOGITS
    ament
    0.07
     Modern
    0.07
     options
    0.06
     replacement
    0.06
     remedy
    0.06
     Options
    0.06
    eway
    0.06
     complaints
    0.06
    _OPTIONS
    0.06
    567
    0.06
    Activations Density 0.026%

    No Known Activations