© 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. 89520
    Prev
    Next
    INDEX
    Explanations

    references to blog content

    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
    ActionCreators
    -0.08
    odef
    -0.07
    legt
    -0.07
     ngang
    -0.07
    avez
    -0.07
    룬
    -0.07
     Zaman
    -0.07
    Ñıн
    -0.07
    weeted
    -0.07
    alto
    -0.07
    POSITIVE LOGITS
    tract
    0.06
    ette
    0.06
     Boss
    0.06
    _gem
    0.06
    otr
    0.05
    877
    0.05
    dings
    0.05
    gie
    0.05
     boss
    0.05
    pac
    0.05
    Activations Density 0.000%

    No Known Activations