© 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. 57035
    Prev
    Next
    INDEX
    Explanations

    patterns related to secrecy and hidden agendas

    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
    ino
    -0.07
    linger
    -0.06
    æĺĵ
    -0.06
    емо
    -0.06
    817
    -0.06
    é§
    -0.06
    emo
    -0.06
    anian
    -0.06
    anni
    -0.06
    oppel
    -0.06
    POSITIVE LOGITS
     simply
    0.14
     crypt
    0.12
     merely
    0.11
     simplement
    0.11
     vague
    0.11
     nothing
    0.10
     only
    0.10
    crypt
    0.10
     neither
    0.09
     пÑĢоÑģÑĤо
    0.08
    Activations Density 0.113%

    No Known Activations