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. 43970
    Prev
    Next
    INDEX
    Explanations

    the word "get" and its variations in different 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
    olis
    -0.06
    ãĤĪãģĨ
    -0.06
    /misc
    -0.06
    onec
    -0.06
    rib
    -0.06
    andering
    -0.06
    reet
    -0.06
    iyan
    -0.06
    akis
    -0.05
    apult
    -0.05
    POSITIVE LOGITS
     over
    0.13
     past
    0.12
     used
    0.11
     through
    0.10
     why
    0.09
    past
    0.09
     passed
    0.09
     över
    0.09
     around
    0.09
    è¿ĩåİ»
    0.09
    Activations Density 0.016%

    No Known Activations