© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97055
    Prev
    Next
    INDEX
    Explanations

    references to adding or including ingredients in recipes

    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
    iple
    -0.08
    ifies
    -0.07
    phinx
    -0.07
    iped
    -0.07
    oya
    -0.07
    enger
    -0.07
    akit
    -0.07
    ripper
    -0.06
    ItemAt
    -0.06
    @Spring
    -0.06
    POSITIVE LOGITS
     alma
    0.07
    atto
    0.06
     analog
    0.06
    BASE
    0.06
     Stafford
    0.06
     Analog
    0.06
     chatte
    0.05
     lượng
    0.05
     fucks
    0.05
     to
    0.05
    Activations Density 0.022%

    No Known Activations