© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 27898
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrive" and its variations

    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
    خاÙĨÙĩ
    -0.15
    elif
    -0.14
    emp
    -0.14
    ÙħÙħ
    -0.14
     Hick
    -0.14
    inely
    -0.14
    ol
    -0.13
    empor
    -0.13
    омеÑĢ
    -0.13
    anna
    -0.13
    POSITIVE LOGITS
    angement
    0.28
    anged
    0.26
    hythm
    0.25
     Arr
    0.24
    anging
    0.22
    ivals
    0.22
    ,arr
    0.20
    .asList
    0.19
     arr
    0.18
    aign
    0.18
    Activations Density 0.010%

    No Known Activations