© 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. 17-LLAMASCOPE-RES-131K
    11. 126180
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "besides."

    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
    ovÄĽ
    -0.08
    tober
    -0.08
    reon
    -0.07
    vs
    -0.07
    ëĭī
    -0.07
    å¯Ł
    -0.07
    erase
    -0.06
    isha
    -0.06
    locker
    -0.06
    .Aggressive
    -0.06
    POSITIVE LOGITS
     being
    0.09
    enger
    0.09
    ness
    0.08
    being
    0.07
    acen
    0.07
    engers
    0.07
    664
    0.06
    ment
    0.06
     noting
    0.06
    pector
    0.06
    Activations Density 0.005%

    No Known Activations