Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57438
    Prev
    Next
    INDEX
    Explanations

    themes relating to social justice and ideology

    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
     would
    -0.07
    would
    -0.07
     Would
    -0.07
    Would
    -0.07
    oint
    -0.07
     Wit
    -0.07
    ottom
    -0.07
    elpers
    -0.07
    etus
    -0.07
    atch
    -0.06
    POSITIVE LOGITS
     becomes
    0.08
     tend
    0.08
     tends
    0.07
     it
    0.07
     obvykle
    0.07
     usually
    0.07
     results
    0.06
     result
    0.06
     become
    0.06
     Clair
    0.06
    Activations Density 0.031%

    No Known Activations