© 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. 28916
    Prev
    Next
    INDEX
    Explanations

    references to formal categorizations or listings

    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
    ising
    -0.08
    isay
    -0.07
    igy
    -0.07
    á»Ļng
    -0.07
    bia
    -0.07
    uman
    -0.07
    ainless
    -0.07
    ä¸ĭåİ»
    -0.07
    nost
    -0.06
    ISED
    -0.06
    POSITIVE LOGITS
    agus
    0.06
    orra
    0.06
     Bow
    0.06
    car
    0.06
    orges
    0.06
    èĮ¨
    0.06
    æ¾
    0.06
     Imm
    0.06
     Affero
    0.06
    DSA
    0.06
    Activations Density 0.001%

    No Known Activations