© 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. 16352
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to economic or health statistics

    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
    mayan
    -0.09
    ADDE
    -0.08
    deme
    -0.08
    ENOMEM
    -0.08
    ADED
    -0.08
     Karlov
    -0.07
    beeld
    -0.07
    .opendaylight
    -0.07
    ÑģÑĮого
    -0.07
    jde
    -0.07
    POSITIVE LOGITS
    ibs
    0.06
     particulars
    0.06
     folds
    0.06
    nia
    0.06
    umb
    0.06
     Roo
    0.05
    nie
    0.05
    ess
    0.05
    igh
    0.05
    ema
    0.05
    Activations Density 0.020%

    No Known Activations