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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13136
    Prev
    Next
    INDEX
    Explanations

    instances of the word "split" 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
    het
    -0.17
    474
    -0.17
    ensen
    -0.17
    iki
    -0.15
    uest
    -0.14
    irected
    -0.14
    ermen
    -0.14
    WS
    -0.14
    704
    -0.14
    sl
    -0.14
    POSITIVE LOGITS
    ting
    0.34
    tered
    0.28
    TING
    0.24
    tering
    0.23
    ter
    0.23
     apart
    0.21
    (split
    0.20
    tring
    0.20
    TINGS
    0.20
    .Split
    0.20
    Activations Density 0.023%

    No Known Activations