© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 77211
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral standards and choices

    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
    869
    -0.07
    775
    -0.07
    á»ķi
    -0.06
    ugg
    -0.06
    140
    -0.06
     Seam
    -0.06
    hiba
    -0.06
     XX
    -0.06
    lish
    -0.06
     Smy
    -0.06
    POSITIVE LOGITS
    alternate
    0.08
    isd
    0.07
    IEnumerator
    0.07
    mime
    0.07
    memset
    0.06
     uncomment
    0.06
     عزÛĮز
    0.06
    çīĩ
    0.06
    vfs
    0.06
    ĶåĽŀ
    0.06
    Activations Density 0.003%

    No Known Activations