© 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. 24-LLAMASCOPE-RES-32K
    11. 18903
    Prev
    Next
    INDEX
    Explanations

    items and components related to vaping and nicotine products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.18
     неÑģп
    -0.17
    $MESS
    -0.17
    æı
    -0.15
    ضÙĪ
    -0.15
     GUIStyle
    -0.15
    [js
    -0.15
    elter
    -0.15
    ervas
    -0.15
    SKI
    -0.14
    POSITIVE LOGITS
     vape
    0.29
     Ju
    0.27
     pod
    0.27
     vaping
    0.27
     flavors
    0.25
     flavor
    0.24
    Ju
    0.23
     Pod
    0.23
     EVAL
    0.22
     e
    0.22
    Activations Density 0.010%

    No Known Activations