© 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. 5-LLAMASCOPE-RES-131K
    11. 126637
    Prev
    Next
    INDEX
    Explanations

    references to trustees or board members in an organization

    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
    ertz
    -0.08
    illac
    -0.07
    bert
    -0.07
    rijk
    -0.07
    lico
    -0.07
    iffin
    -0.07
    ercul
    -0.07
    tplib
    -0.07
    ichen
    -0.07
     çap
    -0.07
    POSITIVE LOGITS
    aler
    0.06
    Spoiler
    0.06
    §è¡Į
    0.06
    asts
    0.06
    chia
    0.06
    iland
    0.06
    spo
    0.06
    ors
    0.06
    362
    0.05
    /prom
    0.05
    Activations Density 0.003%

    No Known Activations