© 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. 21087
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refer" and its variations, indicating connections or citations in the text

    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
    spacer
    -0.19
    ery
    -0.18
    elier
    -0.17
    ury
    -0.16
    iface
    -0.15
    ylon
    -0.14
    el
    -0.14
    aine
    -0.14
    edException
    -0.14
    yan
    -0.14
    POSITIVE LOGITS
    ential
    0.24
    entially
    0.23
    encing
    0.22
    endum
    0.22
    refer
    0.20
     refer
    0.20
    rence
    0.20
    (reference
    0.19
     Refer
    0.19
    .Reference
    0.19
    Activations Density 0.022%

    No Known Activations