© 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. 71171
    Prev
    Next
    INDEX
    Explanations

    numerical criteria and measurements, particularly in academic and professional contexts

    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
    彩票
    -0.09
    ÑģÑĤÑİ
    -0.08
    ìłĿ
    -0.07
    ÑĢÑĥж
    -0.07
    .opendaylight
    -0.07
    ongsTo
    -0.07
    .communic
    -0.07
    ëģĶ
    -0.07
    .epam
    -0.07
    ÐĬ
    -0.07
    POSITIVE LOGITS
     extrem
    0.06
    aset
    0.05
    Ta
    0.05
    -
    0.05
    ÙĬÙĦÙħ
    0.05
     dah
    0.05
    Da
    0.05
     fashion
    0.05
    athan
    0.05
    notation
    0.05
    Activations Density 0.057%

    No Known Activations