© 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. 1055
    Prev
    Next
    INDEX
    Explanations

    scientific assertions and counterarguments about evidence

    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
    /cms
    -0.06
    onia
    -0.06
     es
    -0.06
     Destiny
    -0.06
     Karma
    -0.05
     اÙĦبد
    -0.05
    ana
    -0.05
    709
    -0.05
    atta
    -0.05
     certain
    -0.05
    POSITIVE LOGITS
    åĪ°åºķ
    0.08
     UNKNOWN
    0.07
     possibility
    0.07
    grily
    0.07
    riangle
    0.07
     POSSIBILITY
    0.07
    ä¸įçŁ¥éģĵ
    0.07
    stad
    0.07
     lehet
    0.07
    unden
    0.07
    Activations Density 0.035%

    No Known Activations