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. 43916
    Prev
    Next
    INDEX
    Explanations

    instances of the word "conjunct" or related forms in various contexts

    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
    landa
    -0.07
    chodu
    -0.07
    linger
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    lena
    -0.07
    klady
    -0.07
    chyb
    -0.06
    acha
    -0.06
     Hud
    -0.06
    lenen
    -0.06
    POSITIVE LOGITS
    ure
    0.17
    unct
    0.16
    ures
    0.16
    ured
    0.16
    uring
    0.15
    urers
    0.14
    uncture
    0.14
    urer
    0.14
    our
    0.13
    ugal
    0.13
    Activations Density 0.006%

    No Known Activations