© 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. 17-LLAMASCOPE-RES-131K
    11. 126851
    Prev
    Next
    INDEX
    Explanations

    discussions around proposals and outcomes related to policy or initiatives

    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
    ako
    -0.07
    686
    -0.07
    .cz
    -0.07
     GetString
    -0.06
     Hue
    -0.06
    κοÏį
    -0.06
    rim
    -0.06
     teg
    -0.06
    stoff
    -0.06
     Weed
    -0.06
    POSITIVE LOGITS
    âĢİ
    0.06
    prec
    0.06
    rary
    0.06
     gram
    0.06
    jiang
    0.06
     particular
    0.06
    ourn
    0.05
    èĥ½å¤Ł
    0.05
    Persistent
    0.05
     precip
    0.05
    Activations Density 0.002%

    No Known Activations