© 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. 124991
    Prev
    Next
    INDEX
    Explanations

    references to social structures and inequalities

    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
    íĨłíĨł
    -0.07
    RTOS
    -0.07
     Sesso
    -0.06
    iedo
    -0.06
    arten
    -0.06
    opro
    -0.06
     (&
    -0.06
    avo
    -0.06
    orgia
    -0.06
    .sponge
    -0.06
    POSITIVE LOGITS
     perhaps
    0.19
     maybe
    0.17
    perhaps
    0.14
     Perhaps
    0.14
    maybe
    0.14
    ?↵
    0.13
    ?
    0.13
    Perhaps
    0.13
     Maybe
    0.12
    Maybe
    0.11
    Activations Density 0.120%

    No Known Activations