© 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. 24-LLAMASCOPE-RES-32K
    11. 8194
    Prev
    Next
    INDEX
    Explanations

    expressions related to loss and the emotional impact of grief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¥ãĥ¼
    -0.15
     ::::::::
    -0.14
    ία
    -0.14
    اÙĪت
    -0.13
    ipient
    -0.13
     bele
    -0.13
    izu
    -0.13
    Ñĥки
    -0.12
    NTAX
    -0.12
    defgroup
    -0.12
    POSITIVE LOGITS
     loss
    1.10
     lost
    1.05
     lose
    0.98
    loss
    0.95
     Loss
    0.95
     losses
    0.94
     losing
    0.91
    Loss
    0.91
    lost
    0.90
    -loss
    0.90
    Activations Density 0.440%

    No Known Activations