© 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. 74696
    Prev
    Next
    INDEX
    Explanations

    instances of action and events related to computer usage

    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
    Tokens
    -0.07
     tokens
    -0.06
     post
    -0.06
    Radio
    -0.06
     Marshall
    -0.06
     Honest
    -0.06
    radio
    -0.06
    åde
    -0.06
     Fe
    -0.06
     Handy
    -0.06
    POSITIVE LOGITS
     Interface
    0.08
    _interface
    0.07
    -interface
    0.07
     backlog
    0.07
    aris
    0.06
    Interface
    0.06
    Ħĸ
    0.06
    anton
    0.06
     interface
    0.06
    «ĺ
    0.06
    Activations Density 0.018%

    No Known Activations