© 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. 76832
    Prev
    Next
    INDEX
    Explanations

    technical details about calibration and adjustment processes

    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
    ednou
    -0.07
     rupture
    -0.07
     rupt
    -0.07
    ansi
    -0.06
     اÙĦعÙħ
    -0.06
     morality
    -0.06
    æ·»
    -0.06
    ember
    -0.06
    PACKAGE
    -0.06
    scaling
    -0.06
    POSITIVE LOGITS
     Vladim
    0.08
    orrect
    0.07
     tuning
    0.07
     correct
    0.07
    correct
    0.07
    áÄį
    0.07
     adjustment
    0.07
    sett
    0.06
    .correct
    0.06
     settling
    0.06
    Activations Density 0.123%

    No Known Activations