© 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. 119495
    Prev
    Next
    INDEX
    Explanations

    mentions of specific nouns or unique terms related to various subjects

    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
    rop
    -0.07
    ubbo
    -0.06
    碼
    -0.06
    AZY
    -0.06
    hcp
    -0.06
    pcodes
    -0.06
    à¸ı
    -0.06
    ató
    -0.06
    nee
    -0.06
    ropdown
    -0.06
    POSITIVE LOGITS
     although
    0.32
    although
    0.29
     though
    0.23
     Although
    0.22
     aunque
    0.22
    Although
    0.21
    though
    0.20
     ÑħоÑĤÑı
    0.17
    èĻ½çĦ¶
    0.16
     Though
    0.15
    Activations Density 0.181%

    No Known Activations