© 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. 106428
    Prev
    Next
    INDEX
    Explanations

    instances of unexpected events or occurrences

    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
    ropdown
    -0.07
    quent
    -0.07
    egral
    -0.06
    orners
    -0.06
    906
    -0.06
    ÄĻp
    -0.06
    errupt
    -0.06
    ÑĢÑĥн
    -0.06
    pletion
    -0.06
    025
    -0.06
    POSITIVE LOGITS
    ãĤ·ãĥªãĥ¼ãĤº
    0.07
     Realty
    0.07
    atra
    0.07
    kol
    0.06
     colum
    0.06
    -REAL
    0.06
    rell
    0.06
     Relief
    0.06
    imax
    0.06
    shima
    0.06
    Activations Density 0.000%

    No Known Activations