© 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. 93704
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to informative updates, guidelines, and recommendations

    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
    éĴ®
    -0.08
     helicopt
    -0.08
    Æ°Æ¡ng
    -0.07
    ãĤ¤ãĤº
    -0.07
    .getElements
    -0.07
    áºŃy
    -0.07
    ÑģÑİ
    -0.07
     treff
    -0.07
    .↵↵↵↵↵↵↵↵
    -0.07
    WITHOUT
    -0.07
    POSITIVE LOGITS
     (?)
    0.07
    :
    0.06
    inee
    0.06
    -ish
    0.06
    iblings
    0.06
    ertext
    0.06
    .doc
    0.06
    imal
    0.06
    minent
    0.06
    rellas
    0.05
    Activations Density 0.039%

    No Known Activations