© 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. 125849
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions to sign up or register for events

    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
    etri
    -0.07
    idon
    -0.06
    /version
    -0.06
    èĿ
    -0.06
    ntl
    -0.06
    glich
    -0.06
    abcdef
    -0.06
    inq
    -0.06
    igan
    -0.06
    bole
    -0.06
    POSITIVE LOGITS
     visit
    0.09
     visiting
    0.09
     simply
    0.08
    मत
    0.07
     refer
    0.07
    Simply
    0.07
     Simply
    0.07
    hek
    0.07
     consulting
    0.07
    bac
    0.07
    Activations Density 0.009%

    No Known Activations