© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118488
    Prev
    Next
    INDEX
    Explanations

    references to national and military entities

    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
    ceptar
    -0.08
    illions
    -0.07
    .Modules
    -0.07
    .ReadAll
    -0.07
    enia
    -0.06
    íĥĿ
    -0.06
    endar
    -0.06
    UCT
    -0.06
    alan
    -0.06
    ikler
    -0.06
    POSITIVE LOGITS
     anniversary
    0.07
    TEE
    0.07
    391
    0.06
    481
    0.06
    ousand
    0.06
    tee
    0.06
     Plat
    0.06
     baseman
    0.06
    ãĥ¼ãĥĸ
    0.06
     exited
    0.06
    Activations Density 0.063%

    No Known Activations