© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108605
    Prev
    Next
    INDEX
    Explanations

    phrases about human identity and existence

    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
    filer
    -0.08
    à¹Ģà¸ĭà¸Ńร
    -0.08
    elic
    -0.08
    ksam
    -0.07
    kie
    -0.07
    essen
    -0.07
    etics
    -0.07
    ITHER
    -0.07
    apur
    -0.07
    theid
    -0.07
    POSITIVE LOGITS
     merely
    0.06
     cust
    0.06
     Cust
    0.06
    chrom
    0.05
    ust
    0.05
    only
    0.05
     birth
    0.05
     WebDriver
    0.05
     ...
    0.05
    pton
    0.05
    Activations Density 0.027%

    No Known Activations