© 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. 83105
    Prev
    Next
    INDEX
    Explanations

    phrases indicating biased or preconceived attitudes and decisions

    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
    ÐĴС
    -0.06
     afterward
    -0.06
    nech
    -0.06
    ráv
    -0.06
    emy
    -0.06
     interim
    -0.06
    oord
    -0.06
    lac
    -0.06
    ãĥ¬ãĥ¼
    -0.06
     passing
    -0.05
    POSITIVE LOGITS
     bevor
    0.11
     before
    0.10
     antes
    0.10
    before
    0.10
     trÆ°á»Ľc
    0.10
     Already
    0.10
     anticipated
    0.10
     already
    0.10
     BEFORE
    0.09
    æĹ©
    0.09
    Activations Density 0.051%

    No Known Activations