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. 31-LLAMASCOPE-RES-131K
    6. 44005
    Prev
    Next
    INDEX
    Explanations

    phrases containing the preposition "with."

    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
    gether
    -0.09
     æ´
    -0.08
     With
    -0.07
     with
    -0.07
    jeme
    -0.07
    ardu
    -0.07
    /help
    -0.07
    builtin
    -0.07
    ffect
    -0.07
    aleigh
    -0.07
    POSITIVE LOGITS
    inside
    0.12
     out
    0.09
    al
    0.09
     none
    0.09
    none
    0.08
     admire
    0.08
     reference
    0.08
     regards
    0.07
    ins
    0.07
     appreciate
    0.07
    Activations Density 0.009%

    No Known Activations