© 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. 17-LLAMASCOPE-RES-131K
    11. 56682
    Prev
    Next
    INDEX
    Explanations

    phrases related to forward-looking statements and financial disclosures

    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
     tet
    -0.06
    ÑijÑĤ
    -0.06
    orny
    -0.06
     fellows
    -0.06
    å©
    -0.06
    à¥įवय
    -0.06
    clipse
    -0.06
    tul
    -0.06
    otch
    -0.06
    elia
    -0.06
    POSITIVE LOGITS
     forward
    0.08
    Forward
    0.08
    _SAFE
    0.07
     Forward
    0.07
    forward
    0.07
    .Safe
    0.07
    _forward
    0.06
     contained
    0.06
     stretch
    0.06
    .forward
    0.06
    Activations Density 0.006%

    No Known Activations