© 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. 5-LLAMASCOPE-RES-131K
    11. 125702
    Prev
    Next
    INDEX
    Explanations

    details regarding industrial equipment and processes

    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
     поÑĪ
    -0.06
    passwd
    -0.06
     {.
    -0.06
    üme
    -0.06
     Poh
    -0.06
    agner
    -0.06
    inan
    -0.06
    ager
    -0.06
    alaria
    -0.06
    kah
    -0.06
    POSITIVE LOGITS
    .opens
    0.07
     probs
    0.07
    lope
    0.07
    .tp
    0.06
    edral
    0.06
     BirliÄŁi
    0.06
    ACP
    0.06
     @$_
    0.06
     prob
    0.06
    digest
    0.06
    Activations Density 0.040%

    No Known Activations