Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106658
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or significance

    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
    	ULONG
    -0.07
    ãĥ¬ãĥ¼
    -0.07
    asia
    -0.07
    ÐĺТ
    -0.07
    RefCount
    -0.07
    ÛĮد
    -0.07
    ฯ
    -0.07
    Ấ
    -0.07
    umi
    -0.07
    .Skin
    -0.07
    POSITIVE LOGITS
    mlink
    0.07
     present
    0.07
    ostel
    0.06
    ernen
    0.06
     Dün
    0.06
     manufacture
    0.06
     destinationViewController
    0.06
    žil
    0.05
     devote
    0.05
    oval
    0.05
    Activations Density 0.513%

    No Known Activations