© 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. 69530
    Prev
    Next
    INDEX
    Explanations

    discussions about various services and their impacts

    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
     Ãľlke
    -0.06
     S
    -0.06
    @student
    -0.06
    urgy
    -0.06
    allah
    -0.06
    _pars
    -0.06
     Jo
    -0.06
    uel
    -0.06
     tinder
    -0.05
     etc
    -0.05
    POSITIVE LOGITS
     including
    0.11
    åĮħæĭ¬
    0.10
    including
    0.10
     ranging
    0.10
     vÄįetnÄĽ
    0.09
     INCLUDING
    0.09
     Including
    0.09
    Including
    0.08
     besides
    0.08
     kromÄĽ
    0.08
    Activations Density 0.045%

    No Known Activations