© 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. 128585
    Prev
    Next
    INDEX
    Explanations

    phrases that describe challenges and the effort required to achieve recognition and respect

    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
    nul
    -0.07
     âĹĦ
    -0.07
    ori
    -0.07
    aney
    -0.07
    .exceptions
    -0.07
    ãģŁãĤī
    -0.07
    glob
    -0.06
     nob
    -0.06
     privacy
    -0.06
     pur
    -0.06
    POSITIVE LOGITS
     females
    0.07
    arkin
    0.06
     female
    0.06
     Female
    0.06
     Fem
    0.06
    çĶ·æĢ§
    0.06
     misogyn
    0.06
     ìŬìĦ±
    0.06
    ipa
    0.06
     male
    0.06
    Activations Density 0.024%

    No Known Activations