© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    references to population dynamics and social issues

    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
     much
    -0.07
     must
    -0.06
    umd
    -0.06
    ils
    -0.06
     quite
    -0.06
     last
    -0.05
     might
    -0.05
    much
    -0.05
    arf
    -0.05
     still
    -0.05
    POSITIVE LOGITS
     cÃłng
    0.12
    -than
    0.08
    than
    0.07
    è¶Ĭ
    0.07
    _than
    0.07
    artner
    0.07
     than
    0.07
     THAN
    0.07
    _TP
    0.07
    æ®Ĭ
    0.07
    Activations Density 0.009%

    No Known Activations