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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 128952
    Prev
    Next
    INDEX
    Explanations

    concepts related to improvement and protection

    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
    abant
    -0.08
    -UA
    -0.08
    ÑĸÑĶ
    -0.08
    _OW
    -0.07
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.07
    âĢĮاÙĨ
    -0.07
     Hunger
    -0.07
    acid
    -0.07
    uese
    -0.07
    onsense
    -0.07
    POSITIVE LOGITS
     hopefully
    0.08
     better
    0.07
     emphasis
    0.07
     later
    0.06
     effect
    0.06
    .
    0.06
     respectively
    0.06
     possible
    0.06
    0.06
     its
    0.06
    Activations Density 0.203%

    No Known Activations