© 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. 3935
    Prev
    Next
    INDEX
    Explanations

    elements related to conjunctions, quantities, and references to collections or lists

    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
     β
    -0.24
     ÎĴ
    -0.23
     bacteria
    -0.23
     bishop
    -0.22
     biology
    -0.22
    β
    -0.22
     beta
    -0.21
     Bishop
    -0.21
    .beta
    -0.21
    beta
    -0.20
    POSITIVE LOGITS
    unbind
    0.19
     unb
    0.19
     worst
    0.18
    .unbind
    0.17
     Worst
    0.17
    wor
    0.15
     worse
    0.15
    iya
    0.15
    ITES
    0.15
    bum
    0.15
    Activations Density 0.287%

    No Known Activations