© 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. 106381
    Prev
    Next
    INDEX
    Explanations

    comparative statistics related to rankings or positions

    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
    ÑģоÑĤ
    -0.08
    ForRow
    -0.08
    kup
    -0.07
    eyse
    -0.07
    nika
    -0.07
    izzo
    -0.07
     nues
    -0.07
    lse
    -0.07
    ottle
    -0.07
    loon
    -0.07
    POSITIVE LOGITS
     sublicense
    0.06
    168
    0.06
     with
    0.06
    æ´»
    0.06
    apol
    0.06
    é
    0.06
     slightly
    0.06
     ones
    0.06
    0.05
     bare
    0.05
    Activations Density 0.016%

    No Known Activations