© 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. 125464
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting in 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
    706
    -0.09
    adal
    -0.07
    265
    -0.07
    :↵↵↵↵↵↵
    -0.07
     acomp
    -0.07
    _marshall
    -0.06
    ritis
    -0.06
    Äŀ
    -0.06
    cion
    -0.06
    Ãļ
    -0.06
    POSITIVE LOGITS
     then
    0.16
    then
    0.15
     Then
    0.14
     THEN
    0.13
    Then
    0.13
    çĦ¶åIJİ
    0.10
    	then
    0.10
    THEN
    0.10
     entonces
    0.09
    .Then
    0.09
    Activations Density 0.039%

    No Known Activations