© 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. 4978
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and commands

    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
     shortest
    -0.08
     length
    -0.08
     shortened
    -0.07
    éķ¿åº¦
    -0.07
     shorter
    -0.07
    -length
    -0.07
    erin
    -0.07
    ãģĭãģij
    -0.07
    _length
    -0.07
    istrar
    -0.07
    POSITIVE LOGITS
     putchar
    0.06
    ami
    0.06
    uro
    0.06
     Rach
    0.06
     Spencer
    0.06
    amin
    0.05
     lateral
    0.05
    pg
    0.05
     c
    0.05
     amort
    0.05
    Activations Density 0.036%

    No Known Activations