Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 2694
    Prev
    Next
    INDEX
    Explanations

    superlative expressions indicating size, influence, or quality

    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
    asal
    -0.14
    edn
    -0.14
    fen
    -0.14
    olon
    -0.14
    {:
    -0.14
     sund
    -0.13
    ëĶ©
    -0.13
    祥
    -0.13
     incon
    -0.13
     anale
    -0.13
    POSITIVE LOGITS
    uster
    0.15
    oine
    0.15
    ÎĦ
    0.15
    bil
    0.15
     Bil
    0.15
    æĶ¹
    0.15
    opoulos
    0.15
     finely
    0.14
    ignum
    0.14
    loi
    0.14
    Activations Density 0.027%

    No Known Activations