© 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. 15-LLAMASCOPE-RES-131K
    11. 90464
    Prev
    Next
    INDEX
    Explanations

    discussions about laboratory equipment and its accessibility

    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
    orman
    -0.07
     uniform
    -0.06
    zier
    -0.06
    еÑĢÑĭ
    -0.06
    asty
    -0.06
     Dun
    -0.06
    atra
    -0.06
     OBS
    -0.06
    å¿
    -0.06
    ovah
    -0.06
    POSITIVE LOGITS
     equipment
    0.08
    elts
    0.07
    bourg
    0.07
    isque
    0.07
    åĿı
    0.07
    ñana
    0.07
    indre
    0.07
    ç¨
    0.07
    ANGES
    0.06
    IDAD
    0.06
    Activations Density 0.011%

    No Known Activations