Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40503
    Prev
    Next
    INDEX
    Explanations

    references to nuts and nut-related products

    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
    ureka
    -0.07
     Twe
    -0.07
     proprietary
    -0.07
    pageTitle
    -0.07
    hood
    -0.07
    ampler
    -0.07
    edList
    -0.06
    readcr
    -0.06
    ossier
    -0.06
    hub
    -0.06
    POSITIVE LOGITS
    ritional
    0.11
    ty
    0.10
    meg
    0.09
    ten
    0.09
    rient
    0.09
    ters
    0.08
    rients
    0.08
    rition
    0.08
    shell
    0.08
    ted
    0.07
    Activations Density 0.019%

    No Known Activations