© 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. 71408
    Prev
    Next
    INDEX
    Explanations

    phrases that involve conjunctions and their relationships within the text

    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
    letic
    -0.07
    éŀ
    -0.07
    pery
    -0.06
     dün
    -0.06
    orte
    -0.06
    AGO
    -0.06
    ã
    -0.06
    ä¸Ńãģ«
    -0.06
    ç¸
    -0.06
    ãģ¾ãģļ
    -0.06
    POSITIVE LOGITS
     others
    0.11
     Others
    0.10
     another
    0.09
    Others
    0.08
    others
    0.08
    another
    0.08
     whereas
    0.08
     similarly
    0.08
     likewise
    0.07
    'autres
    0.07
    Activations Density 0.091%

    No Known Activations