© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or association

    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
    usted
    -0.06
     reversible
    -0.06
    .lib
    -0.06
    anner
    -0.05
     Grass
    -0.05
    udio
    -0.05
     Kraft
    -0.05
     durumda
    -0.05
     Ñģебе
    -0.05
    ants
    -0.05
    POSITIVE LOGITS
    enk
    0.08
    Äįe
    0.07
    'gc
    0.07
    ì¦Į
    0.07
    CTL
    0.07
    itle
    0.07
    æ°§
    0.06
    iddet
    0.06
     eff
    0.06
    ertiary
    0.06
    Activations Density 0.010%

    No Known Activations