© 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. 16142
    Prev
    Next
    INDEX
    Explanations

    negative news affecting various groups of people

    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
    ä¸įåı¯
    -0.07
    aris
    -0.07
    chez
    -0.07
    IRR
    -0.06
    uzey
    -0.06
     adulte
    -0.06
    Ä©nh
    -0.06
    SOR
    -0.06
    æīįèĥ½
    -0.06
     addCriterion
    -0.06
    POSITIVE LOGITS
     those
    0.10
    éĤ£äºĽ
    0.08
    those
    0.08
     Those
    0.08
     anyone
    0.07
    tplib
    0.07
    æ¦
    0.07
     everyone
    0.07
    ully
    0.06
    Those
    0.06
    Activations Density 0.029%

    No Known Activations