© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128753
    Prev
    Next
    INDEX
    Explanations

    hash tags and section markers in a 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
    edo
    -0.07
     Hlav
    -0.06
    ending
    -0.06
     telefon
    -0.06
    ester
    -0.06
    nell
    -0.06
    antage
    -0.06
     Fre
    -0.06
     Bre
    -0.06
    enable
    -0.06
    POSITIVE LOGITS
    #↵↵
    0.09
    ##↵↵
    0.09
    333
    0.07
     Rag
    0.07
    ropp
    0.07
    InBackground
    0.07
    AndWait
    0.06
    inho
    0.06
    ###↵↵
    0.06
    æİĽ
    0.06
    Activations Density 0.004%

    No Known Activations