© 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. 129759
    Prev
    Next
    INDEX
    Explanations

    structured data or references within a biographical context

    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
     ownership
    -0.06
     MPL
    -0.06
    ERGE
    -0.06
     Muj
    -0.06
     fallen
    -0.06
    Ownership
    -0.06
    opes
    -0.06
    DCF
    -0.06
    tere
    -0.06
    /REC
    -0.06
    POSITIVE LOGITS
     Born
    0.10
     bio
    0.09
    bio
    0.09
    çĶŁ
    0.09
     born
    0.08
     bi
    0.08
     biography
    0.08
    Bio
    0.08
    cco
    0.08
     BIO
    0.08
    Activations Density 0.025%

    No Known Activations