© 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. 60099
    Prev
    Next
    INDEX
    Explanations

    references to the human impact of social issues, particularly immigration and trauma

    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
     pillar
    -0.07
    iel
    -0.06
     fav
    -0.06
    å»Ĭ
    -0.06
    éĥİ
    -0.06
     mell
    -0.06
    ysi
    -0.06
     Shelter
    -0.06
    سر
    -0.06
    .runtime
    -0.06
    POSITIVE LOGITS
     individual
    0.10
    individual
    0.09
     human
    0.09
    human
    0.09
     individ
    0.08
     Individual
    0.08
     abstract
    0.08
    _individual
    0.08
    Individual
    0.08
     numbers
    0.08
    Activations Density 0.030%

    No Known Activations