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

    Neuronpedia

    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. 20-LLAMASCOPE-RES-32K
    11. 25007
    Prev
    Next
    INDEX
    Explanations

    terms related to disappearance or vanishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aign
    -0.18
    loy
    -0.15
    =".$_
    -0.14
    ollider
    -0.14
    rips
    -0.14
    itle
    -0.14
    gratis
    -0.14
    ding
    -0.14
    åĭĻ
    -0.14
    ylie
    -0.14
    POSITIVE LOGITS
     disappear
    0.36
     disappeared
    0.34
     disappearance
    0.34
     disappearing
    0.34
     disappears
    0.33
     vanish
    0.32
     vanished
    0.31
     van
    0.27
     disappe
    0.26
    vanished
    0.25
    Activations Density 0.104%

    No Known Activations