© 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. 40645
    Prev
    Next
    INDEX
    Explanations

    negative qualities associated with false friendships

    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
    -0.07
    lette
    -0.07
    ë¡Ŀ
    -0.07
     fetisch
    -0.07
    WND
    -0.07
    lete
    -0.07
    Appending
    -0.07
    _OW
    -0.07
    .templates
    -0.07
    lettes
    -0.06
    POSITIVE LOGITS
     fake
    0.08
     Hyp
    0.07
     false
    0.07
     masks
    0.07
     artificial
    0.07
     opportun
    0.07
     wolves
    0.06
     лиÑĨ
    0.06
     mask
    0.06
    hyp
    0.06
    Activations Density 0.076%

    No Known Activations