© 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. 17-LLAMASCOPE-RES-131K
    11. 119554
    Prev
    Next
    INDEX
    Explanations

    indicators of news and commentary articles

    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
    abric
    -0.07
    iom
    -0.07
    etty
    -0.07
    uppe
    -0.06
    eder
    -0.06
    amat
    -0.06
    iddi
    -0.06
    avr
    -0.06
    brook
    -0.06
    å©·
    -0.06
    POSITIVE LOGITS
    ucher
    0.07
    _OPTS
    0.07
    çĻ¾
    0.07
    aticon
    0.07
    uchs
    0.06
     ple
    0.06
    017
    0.06
    ãĥģãĥ¥
    0.06
    ìĹĨëĬĶ
    0.06
     çķĻ
    0.06
    Activations Density 0.051%

    No Known Activations