© 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. 125331
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to size, length, or duration

    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
    828
    -0.06
     paran
    -0.06
    vm
    -0.06
     Moor
    -0.06
     Crane
    -0.06
     Operator
    -0.05
    zon
    -0.05
    ollo
    -0.05
    ooth
    -0.05
     Wells
    -0.05
    POSITIVE LOGITS
    ostel
    0.08
    arias
    0.07
     size
    0.07
    iba
    0.07
    ξη
    0.07
    imeline
    0.07
     nature
    0.07
    agn
    0.06
    okers
    0.06
    ickers
    0.06
    Activations Density 0.017%

    No Known Activations