Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5689
    Prev
    Next
    INDEX
    Explanations

    occurrences of future actions or commitments

    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
    osals
    -0.07
    nip
    -0.07
    abor
    -0.07
    åĩºåİ»
    -0.07
     öden
    -0.07
    ÑĢÑİ
    -0.06
    ãĥ
    -0.06
    ngo
    -0.06
    @dynamic
    -0.06
    ivre
    -0.06
    POSITIVE LOGITS
     send
    0.09
     automatically
    0.08
    -send
    0.08
     contact
    0.08
     sends
    0.08
     charge
    0.07
     email
    0.07
    Send
    0.07
     Send
    0.07
     issue
    0.07
    Activations Density 0.035%

    No Known Activations