© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31277
    Prev
    Next
    INDEX
    Explanations

    phrases related to the expansion and improvement of social services and community resources

    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
    å·¦åı³
    -0.06
     Feinstein
    -0.06
    ÙĪاÙĨ
    -0.06
    kes
    -0.06
    quine
    -0.06
     Altern
    -0.06
    uri
    -0.06
    ÙĪع
    -0.06
     Demir
    -0.06
    edis
    -0.05
    POSITIVE LOGITS
     rather
    0.25
     instead
    0.22
    rather
    0.21
    instead
    0.21
     Rather
    0.20
    Rather
    0.19
     Instead
    0.17
    Instead
    0.17
     chứ
    0.17
     вмеÑģÑĤ
    0.14
    Activations Density 0.056%

    No Known Activations