© 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. 78675
    Prev
    Next
    INDEX
    Explanations

    phrases that solicit information or questions directed at the reader

    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
    asi
    -0.07
    çĻº
    -0.07
     forth
    -0.06
    ugs
    -0.06
    ASI
    -0.06
    clusion
    -0.06
    ise
    -0.06
    /std
    -0.06
     UIControl
    -0.06
    èn
    -0.06
    POSITIVE LOGITS
     imagine
    0.09
    aine
    0.07
    adians
    0.06
     please
    0.06
    IGGER
    0.06
    nda
    0.06
     afford
    0.06
     imagining
    0.06
    Imagine
    0.06
     Imagine
    0.06
    Activations Density 0.005%

    No Known Activations