© 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. 22-LLAMASCOPE-RES-32K
    6. 28677
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or functions within technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aña
    -0.15
    å®ļçļĦ
    -0.15
    ulings
    -0.15
    å±Ĭ
    -0.14
    ÄĽt
    -0.14
    eyin
    -0.14
     multiplied
    -0.14
    å®ļ
    -0.14
    ParameterValue
    -0.14
    گرد
    -0.13
    POSITIVE LOGITS
     sum
    0.50
     Sum
    0.46
    sum
    0.46
    -sum
    0.44
    Sum
    0.44
    .sum
    0.41
     SUM
    0.40
     summ
    0.39
     sums
    0.38
    SUM
    0.38
    Activations Density 0.151%

    No Known Activations