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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 755
    Prev
    Next
    INDEX
    Explanations

    concepts related to accountability and transparency in auditing and financial practices

    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
     Ups
    -0.07
    ept
    -0.07
    ocks
    -0.06
    ebo
    -0.06
     Rede
    -0.06
    .Convert
    -0.06
    .converter
    -0.06
    pawn
    -0.06
    icast
    -0.06
    Ups
    -0.06
    POSITIVE LOGITS
    plits
    0.06
    chet
    0.06
    forth
    0.06
    ifa
    0.06
    dna
    0.06
    ubat
    0.06
     å®
    0.06
    oksen
    0.06
    ÙĪغ
    0.06
     Industry
    0.06
    Activations Density 0.002%

    No Known Activations