© 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. 30-LLAMASCOPE-RES-32K
    11. 17387
    Prev
    Next
    INDEX
    Explanations

    phrases related to the benefits of reducing costs and improving efficiency in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iani
    -0.15
    illon
    -0.15
    nero
    -0.14
    UFFIX
    -0.14
    croft
    -0.14
    Slow
    -0.14
     dostate
    -0.14
     Ñģлаб
    -0.13
     unlucky
    -0.13
    UCT
    -0.13
    POSITIVE LOGITS
     saving
    0.48
     saves
    0.47
     save
    0.45
     saved
    0.44
     savings
    0.44
     Saves
    0.41
     Saving
    0.39
    saving
    0.39
    save
    0.38
    èĬĤ
    0.38
    Activations Density 0.607%

    No Known Activations