© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2982
    Prev
    Next
    INDEX
    Explanations

    phrases related to logistical processes or command operations

    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
    .setViewport
    -0.15
    896
    -0.15
    ocache
    -0.14
    ấu
    -0.13
     Reconstruction
    -0.13
    otos
    -0.13
    _SKIP
    -0.13
    omik
    -0.13
     haus
    -0.13
    .Interop
    -0.13
    POSITIVE LOGITS
     Fir
    0.16
    TemplateName
    0.14
    fir
    0.14
    nger
    0.14
     Normal
    0.14
     Conveyor
    0.13
     soul
    0.13
    lish
    0.13
    .lua
    0.13
     shove
    0.13
    Activations Density 0.074%

    No Known Activations