© 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. 40256
    Prev
    Next
    INDEX
    Explanations

    materials associated with quality and craftsmanship in 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
    вÑĥ
    -0.07
     Seal
    -0.07
    kes
    -0.07
     että
    -0.06
    ilians
    -0.06
    ìn
    -0.06
    esser
    -0.06
    기ëıĦ
    -0.06
    agenta
    -0.06
    .codes
    -0.06
    POSITIVE LOGITS
    å¾
    0.06
    lio
    0.06
    )null
    0.06
    won
    0.06
    upp
    0.06
    instead
    0.06
    ien
    0.05
    ãĤµãĥ¼
    0.05
    material
    0.05
    _HT
    0.05
    Activations Density 0.018%

    No Known Activations