© 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. 86218
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and innovation

    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
    agna
    -0.06
     Vera
    -0.06
     Percy
    -0.05
    é¦
    -0.05
    656
    -0.05
    873
    -0.05
     dope
    -0.05
    872
    -0.05
    845
    -0.05
     ris
    -0.05
    POSITIVE LOGITS
    abay
    0.08
    fitness
    0.08
     Blur
    0.08
    ç§Ģ
    0.07
     blur
    0.07
     blurred
    0.07
    /animations
    0.07
     fitness
    0.07
     assort
    0.07
    γει
    0.07
    Activations Density 0.000%

    No Known Activations