© 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. 128614
    Prev
    Next
    INDEX
    Explanations

    values related to passwords and sensitive data

    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
    eson
    -0.07
    ?url
    -0.07
     виконав
    -0.07
    reo
    -0.07
     Äijâu
    -0.07
    .decorate
    -0.07
    ONO
    -0.06
    uae
    -0.06
    duino
    -0.06
     Trie
    -0.06
    POSITIVE LOGITS
    123
    0.08
     secret
    0.07
     Secret
    0.07
    nze
    0.07
     telev
    0.06
    Secret
    0.06
    ÙĦت
    0.06
    ÑĤÑĶ
    0.06
    secret
    0.06
    remember
    0.06
    Activations Density 0.015%

    No Known Activations