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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57640
    Prev
    Next
    INDEX
    Explanations

    references to business relationships and collaborations

    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
    ):?>↵
    -0.07
    izzas
    -0.06
    887
    -0.06
    ASCADE
    -0.06
    ìĦľ
    -0.06
    isen
    -0.06
    ãĥ«ãĥĪ
    -0.06
    renched
    -0.06
    838
    -0.06
    pare
    -0.06
    POSITIVE LOGITS
    á»ģ
    0.08
    igner
    0.07
    /goto
    0.07
    oyer
    0.07
    klad
    0.07
    klady
    0.07
    unfold
    0.06
    exampleModal
    0.06
    createView
    0.06
     Hab
    0.06
    Activations Density 0.007%

    No Known Activations