© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76286
    Prev
    Next
    INDEX
    Explanations

    references to specific statistical data or numerical values

    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
     lam
    -0.08
    ebi
    -0.07
    portun
    -0.07
    elon
    -0.07
    елиÑĩ
    -0.07
    319
    -0.07
    olec
    -0.07
    AccessType
    -0.06
    ugar
    -0.06
    appen
    -0.06
    POSITIVE LOGITS
    bes
    0.07
    rad
    0.06
    ired
    0.06
    ienne
    0.06
    theless
    0.06
    اÛĮØ´
    0.06
     æĪ
    0.06
    217
    0.06
    witch
    0.06
    ven
    0.06
    Activations Density 0.043%

    No Known Activations