© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90429
    Prev
    Next
    INDEX
    Explanations

    elements related to CSS styling and layout properties

    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
     Nej
    -0.06
     movements
    -0.06
     Cant
    -0.06
     loos
    -0.05
     redundant
    -0.05
     IAM
    -0.05
     overhead
    -0.05
     glo
    -0.05
    strup
    -0.05
     Fut
    -0.05
    POSITIVE LOGITS
    .skin
    0.08
    WithTitle
    0.08
    ATUS
    0.08
    rippling
    0.08
    ozilla
    0.07
    ackages
    0.07
    .Args
    0.07
    quential
    0.07
    .EventType
    0.07
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    0.07
    Activations Density 0.020%

    No Known Activations