© 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 EvalsExportsAPI 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. 75022
    Prev
    Next
    INDEX
    Explanations

    mentions of social media profiles and related discussions

    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
    sville
    -0.06
    933
    -0.05
    äºĭ
    -0.05
    EMU
    -0.05
     Claus
    -0.05
     آذ
    -0.05
    olph
    -0.05
    duit
    -0.05
    pedia
    -0.05
     Stern
    -0.05
    POSITIVE LOGITS
     profile
    0.07
    ãģķãĤĵãģ®
    0.07
    profile
    0.06
    ÅĻes
    0.06
     Profile
    0.06
    PRECATED
    0.06
    .micro
    0.06
    alon
    0.06
     Alberto
    0.06
    instanc
    0.06
    Activations Density 0.001%

    No Known Activations