© 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. 119119
    Prev
    Next
    INDEX
    Explanations

    phrases indicating absence or lack of availability

    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
    abi
    -0.07
    datable
    -0.07
    hua
    -0.06
    Ú¯ÙĪ
    -0.06
    inge
    -0.06
    into
    -0.06
    inet
    -0.06
    anz
    -0.06
     ãģĹ
    -0.06
    uat
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.09
     previously
    0.08
     otherwise
    0.08
     necessarily
    0.08
     exist
    0.08
     anywhere
    0.08
    ationally
    0.07
     any
    0.07
     present
    0.07
     exists
    0.07
    Activations Density 0.018%

    No Known Activations