© 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. 17086
    Prev
    Next
    INDEX
    Explanations

    criteria and metrics related to performance assessment or evaluations

    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
     Rena
    -0.08
    lesen
    -0.07
    βά
    -0.07
    LOSS
    -0.07
    ouri
    -0.07
     norge
    -0.07
    UBLE
    -0.07
    anova
    -0.07
    asal
    -0.07
    ÑĪка
    -0.07
    POSITIVE LOGITS
     EITHER
    0.09
    Demon
    0.06
     Demon
    0.06
     Society
    0.06
     Pied
    0.06
    gid
    0.06
     consistently
    0.05
    oir
    0.05
     past
    0.05
     sustained
    0.05
    Activations Density 0.011%

    No Known Activations