© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128560
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to fairness and unfairness

    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
    _lineno
    -0.07
    aho
    -0.07
    egasus
    -0.07
    ลาย
    -0.07
     weg
    -0.07
     phù
    -0.07
    Ïģι
    -0.07
    оÑĢоÑĤ
    -0.07
    endor
    -0.07
    eday
    -0.07
    POSITIVE LOGITS
     fair
    0.08
     unfair
    0.07
    ably
    0.07
    aban
    0.07
    yt
    0.07
     fairness
    0.06
    ness
    0.06
     Fair
    0.06
    Fair
    0.06
    ground
    0.06
    Activations Density 0.014%

    No Known Activations