© 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. 9-LLAMASCOPE-RES-131K
    11. 94299
    Prev
    Next
    INDEX
    Explanations

    keywords related to various forms of communication and technology integration

    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
    .CompareTag
    -0.05
    orte
    -0.05
    éº
    -0.05
    ounters
    -0.05
    }elseif
    -0.05
    329
    -0.05
    иÑĤелÑĮно
    -0.05
    aug
    -0.05
    ((-
    -0.05
    anne
    -0.05
    POSITIVE LOGITS
    SUMER
    0.08
    lant
    0.07
    izr
    0.07
    amedi
    0.07
    efined
    0.07
    adero
    0.07
     Curry
    0.07
    FAST
    0.07
    ìĪľ
    0.07
    zik
    0.07
    Activations Density 0.057%

    No Known Activations