© 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. 31-LLAMASCOPE-RES-32K
    11. 21194
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals in aviation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rovers
    -0.18
     rover
    -0.17
    rox
    -0.16
    runner
    -0.16
     Rogue
    -0.15
    ros
    -0.15
    rove
    -0.15
    岩
    -0.15
    roje
    -0.15
    rot
    -0.15
    POSITIVE LOGITS
     Richard
    1.16
    Richard
    1.08
     Richards
    0.96
     Richardson
    0.89
    rich
    0.82
     rich
    0.81
    Rich
    0.81
     Rich
    0.81
     richness
    0.72
     Richie
    0.71
    Activations Density 0.032%

    No Known Activations