© 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. 40267
    Prev
    Next
    INDEX
    Explanations

    temporal references, particularly the word "on" followed by dates or times

    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
     weekly
    -0.06
     Weeks
    -0.06
     Wikipedia
    -0.06
    IFI
    -0.06
    inen
    -0.06
    uard
    -0.06
     weekend
    -0.06
     weekends
    -0.06
     wiki
    -0.06
     Nu
    -0.05
    POSITIVE LOGITS
    Ïĥον
    0.07
    qualities
    0.07
    estone
    0.07
    -UA
    0.07
    sono
    0.07
    obl
    0.07
    ãĥ³ãĥĸ
    0.07
    arrera
    0.07
    isted
    0.06
    beros
    0.06
    Activations Density 0.008%

    No Known Activations