© 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. 77560
    Prev
    Next
    INDEX
    Explanations

    references to groups of people or entities involved in specific actions or events

    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
    ollapsed
    -0.09
    éli
    -0.07
    iele
    -0.07
    Reviewed
    -0.07
    phalt
    -0.07
    ceased
    -0.07
    UCH
    -0.07
    ất
    -0.06
    CLA
    -0.06
    actories
    -0.06
    POSITIVE LOGITS
    aire
    0.07
     Bris
    0.06
     dec
    0.06
     are
    0.06
    çIJĥ
    0.05
    omin
    0.05
     union
    0.05
    ardin
    0.05
     reactions
    0.05
     jump
    0.05
    Activations Density 0.041%

    No Known Activations