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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 4-LLAMASCOPE-RES-32K
    11. 25517
    Prev
    Next
    INDEX
    Explanations

    phrases conveying a sense of lack or absence, particularly in the context of emotional or material loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.18
    ai
    -0.16
    cie
    -0.15
     bed
    -0.15
    bed
    -0.15
     con
    -0.15
     Artificial
    -0.15
    ure
    -0.14
    868
    -0.14
    (s
    -0.14
    POSITIVE LOGITS
    RuleContext
    0.19
    enaire
    0.19
    ardown
    0.19
    trfs
    0.17
     ÙħعÙĦÙĪÙħات
    0.17
    SharedPointer
    0.17
    BackingField
    0.17
    OffsetTable
    0.16
    -equiv
    0.16
    RuntimeObject
    0.16
    Activations Density 0.137%

    No Known Activations