© 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. 116647
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic devices or accessories

    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
     Inherits
    -0.06
     chiff
    -0.06
     switches
    -0.06
     bearings
    -0.06
     Chips
    -0.06
    ounder
    -0.06
    CHIP
    -0.06
    loat
    -0.06
    ustry
    -0.06
    lyn
    -0.06
    POSITIVE LOGITS
     charging
    0.15
     Charging
    0.15
     charge
    0.13
     Charge
    0.13
     charg
    0.12
    charge
    0.11
     charger
    0.11
     Charg
    0.11
     charged
    0.10
    charging
    0.10
    Activations Density 0.027%

    No Known Activations