© 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. 58682
    Prev
    Next
    INDEX
    Explanations

    evaluative language related to performance and quality assessment

    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
    çĵ
    -0.07
    LOSS
    -0.07
     statuses
    -0.07
    ammer
    -0.07
    ças
    -0.07
    vertime
    -0.07
     Rahmen
    -0.06
    SystemService
    -0.06
    anked
    -0.06
    leck
    -0.06
    POSITIVE LOGITS
     overall
    0.09
     contribution
    0.07
     technical
    0.07
     judges
    0.07
    overall
    0.07
     Overall
    0.07
     ties
    0.07
    Overall
    0.07
     factor
    0.06
    erner
    0.06
    Activations Density 0.010%

    No Known Activations