© 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. 17-LLAMASCOPE-RES-131K
    11. 128177
    Prev
    Next
    INDEX
    Explanations

    actions related to performance and effort in a collaborative context

    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
    ij¸
    -0.06
    ãĥ£
    -0.06
    IDA
    -0.06
     subordinate
    -0.06
     vez
    -0.06
     pit
    -0.06
    046
    -0.06
    isma
    -0.06
    /dc
    -0.06
    _PROC
    -0.06
    POSITIVE LOGITS
     now
    0.09
     currently
    0.08
     presently
    0.07
     increasingly
    0.07
     Currently
    0.07
    now
    0.07
    ensch
    0.07
    currently
    0.07
    Scalars
    0.06
     ÑģейÑĩаÑģ
    0.06
    Activations Density 0.045%

    No Known Activations