© 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. 2-LLAMASCOPE-RES-32K
    11. 1434
    Prev
    Next
    INDEX
    Explanations

    numbers, specifically those related to quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     éĤ
    -0.16
    ãĥ¼ãĤ¸
    -0.16
    iew
    -0.15
    oi
    -0.15
    ury
    -0.15
    etch
    -0.15
    Malloc
    -0.14
     ç·
    -0.14
    ãģ¨ãģĵãĤį
    -0.14
    ieties
    -0.14
    POSITIVE LOGITS
    EDA
    0.15
     proÄį
    0.15
    stru
    0.15
    å¡ļ
    0.15
    elo
    0.15
    066
    0.14
    ÛĮÙĦÛĮ
    0.14
    tility
    0.14
    izoph
    0.14
    omanip
    0.14
    Activations Density 0.006%

    No Known Activations