© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56395
    Prev
    Next
    INDEX
    Explanations

    commas and punctuation that indicate a list or preceding commentary

    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
    okit
    -0.07
    erce
    -0.06
    Plus
    -0.06
    atsu
    -0.06
    press
    -0.06
     Sabha
    -0.06
     ke
    -0.05
    åĶ®
    -0.05
    oki
    -0.05
    addy
    -0.05
    POSITIVE LOGITS
     this
    0.09
     now
    0.08
    esh
    0.07
    ESH
    0.07
     hopefully
    0.07
     tonight
    0.07
     these
    0.07
    this
    0.07
     ìĿ´ë²Ī
    0.07
     THIS
    0.07
    Activations Density 0.020%

    No Known Activations