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. 43518
    Prev
    Next
    INDEX
    Explanations

    components related to veterinary health and animal care

    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
    hiba
    -0.08
    adro
    -0.07
     Hindered
    -0.07
    ultipart
    -0.07
    ÑĤом
    -0.06
    igua
    -0.06
    avenport
    -0.06
     Doctors
    -0.06
    .opendaylight
    -0.06
     Baghd
    -0.06
    POSITIVE LOGITS
     her
    0.11
     herd
    0.11
     Her
    0.10
     Joh
    0.09
     test
    0.09
     premises
    0.09
     milk
    0.09
    her
    0.09
     slaughter
    0.09
     dairy
    0.09
    Activations Density 0.025%

    No Known Activations