© 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. 9-LLAMASCOPE-RES-131K
    11. 95502
    Prev
    Next
    INDEX
    Explanations

    references to styling or formatting elements in web development

    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
    717
    -0.06
    ohl
    -0.06
    onn
    -0.06
    inh
    -0.06
    amp
    -0.06
    045
    -0.06
     Kup
    -0.06
    redients
    -0.06
    plies
    -0.06
    eneric
    -0.06
    POSITIVE LOGITS
     baiser
    0.08
    attern
    0.08
    unter
    0.07
    cki
    0.07
    ãĥ¬ãĥĥãĥĪ
    0.07
     blat
    0.07
    ">//
    0.07
     tard
    0.06
     âĺħ
    0.06
    arten
    0.06
    Activations Density 0.000%

    No Known Activations