© 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. 74862
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various levels and types of government involvement or assistance

    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
    xE
    -0.07
     Walters
    -0.07
    anja
    -0.07
    çĨ
    -0.06
    kee
    -0.06
    ãĥªãĥ³ãĤ°
    -0.06
    appointed
    -0.06
     appoint
    -0.06
    νον
    -0.06
    .nodeType
    -0.06
    POSITIVE LOGITS
     local
    0.14
    -local
    0.14
    local
    0.12
    /local
    0.11
     Local
    0.10
    _local
    0.10
    Local
    0.09
     lokal
    0.09
     LOCAL
    0.09
     locally
    0.09
    Activations Density 0.012%

    No Known Activations