© 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. 8-LLAMASCOPE-RES-32K
    11. 6722
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and operations in the context of programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inx
    -0.17
    _ASSUME
    -0.17
    iÄĻ
    -0.15
     wel
    -0.15
    iw
    -0.15
    enko
    -0.15
    ulk
    -0.14
    readcr
    -0.14
    phans
    -0.14
    TK
    -0.14
    POSITIVE LOGITS
    yers
    0.16
    eras
    0.15
     Russo
    0.14
    iaux
    0.14
    isson
    0.14
    ucch
    0.14
    Ïĥι
    0.14
    arton
    0.14
    -lang
    0.14
    legate
    0.14
    Activations Density 0.069%

    No Known Activations