© 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. 56080
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or possessive forms indicating ownership or relationships

    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
     the
    -0.06
    stown
    -0.06
    azz
    -0.06
    äft
    -0.06
    302
    -0.05
     your
    -0.05
    640
    -0.05
     Nich
    -0.05
    -0.05
    baugh
    -0.05
    POSITIVE LOGITS
    ì§ĢëıĦ
    0.09
     tô
    0.09
    باش
    0.08
     jich
    0.08
    ãĥĨãĥ«
    0.08
    ÙĬدا
    0.08
    [`
    0.08
    jad
    0.08
    IRQ
    0.08
     lesbi
    0.08
    Activations Density 0.035%

    No Known Activations