© 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. 103745
    Prev
    Next
    INDEX
    Explanations

    phrases related to comprehension and understanding

    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
    illi
    -0.07
    zos
    -0.07
    undi
    -0.06
     schema
    -0.06
    epar
    -0.06
    æŃ£
    -0.06
    illy
    -0.06
    ãģĹãģ®
    -0.06
    umper
    -0.06
    akis
    -0.06
    POSITIVE LOGITS
    swire
    0.07
    awns
    0.06
     Compensation
    0.06
    oto
    0.06
    eor
    0.06
    ulus
    0.06
    otland
    0.06
     compens
    0.06
    kin
    0.06
    SYNC
    0.06
    Activations Density 0.006%

    No Known Activations