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. 125589
    Prev
    Next
    INDEX
    Explanations

    various plural nouns related to groups or categories

    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
    umer
    -0.06
    ç³»
    -0.06
    ιÏĥ
    -0.06
    ìĭľëĬĶ
    -0.06
    _MACRO
    -0.06
     Äįin
    -0.06
     ill
    -0.06
     sit
    -0.05
     trust
    -0.05
    ERA
    -0.05
    POSITIVE LOGITS
    yen
    0.08
    Truthy
    0.07
    InstanceState
    0.07
    clair
    0.07
    adj
    0.07
    Į¨
    0.07
    оваÑĢ
    0.07
     Lyons
    0.07
    Insets
    0.07
    oubles
    0.07
    Activations Density 0.040%

    No Known Activations