© 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. 18-LLAMASCOPE-RES-32K
    11. 3878
    Prev
    Next
    INDEX
    Explanations

    significant numerical references and comparisons in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sheldon
    -0.15
    EObject
    -0.15
    ůležit
    -0.14
    [Unit
    -0.13
     liable
    -0.13
     RTVF
    -0.13
    aload
    -0.13
    ROWN
    -0.13
    subtype
    -0.13
    å»ł
    -0.13
    POSITIVE LOGITS
    Aspect
    0.18
     observations
    0.17
     aspect
    0.17
    usher
    0.17
     aspects
    0.17
     points
    0.15
     Aspect
    0.15
     ill
    0.15
    iod
    0.15
    anca
    0.15
    Activations Density 0.264%

    No Known Activations