© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95775
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying updated or informed

    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
    ret
    -0.06
    ol
    -0.06
    ushi
    -0.06
    ripe
    -0.06
    sm
    -0.06
    is
    -0.06
    anes
    -0.06
     cap
    -0.06
    vers
    -0.06
    asco
    -0.05
    POSITIVE LOGITS
    èĬ¬
    0.07
    ADDE
    0.07
    (DBG
    0.07
    vil
    0.07
    _EDITOR
    0.07
    =#
    0.07
    opleft
    0.07
     baiser
    0.07
     åŀ
    0.07
    å¢
    0.06
    Activations Density 0.005%

    No Known Activations