© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94050
    Prev
    Next
    INDEX
    Explanations

    references to scientific disciplines or fields of study

    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
    iffin
    -0.09
    atat
    -0.09
    ataka
    -0.08
    zm
    -0.07
    uien
    -0.07
    uegos
    -0.07
    iate
    -0.07
    zion
    -0.07
    ipt
    -0.07
    Threshold
    -0.07
    POSITIVE LOGITS
     Burnett
    0.06
    upp
    0.06
     imagePath
    0.05
     Carla
    0.05
     Wer
    0.05
    cha
    0.05
     Saunders
    0.05
     exam
    0.05
    rad
    0.05
     Nose
    0.05
    Activations Density 0.001%

    No Known Activations