INDEX

Explanations

connecting words and phrases that indicate causality or relationships in the context of information and explanations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©rica

-0.16

ied

-0.15

enerative

-0.15

ë§¹

-0.14

rito

-0.14

Ã©ric

-0.14

 Prote

-0.14

ardon

-0.14

idy

-0.14

POSITIVE LOGITS

ouri

0.16

ÑĤÐ¸Ð½

0.16

åĪº

0.15

inho

0.14

laÅŁ

0.14

Ø§Ø±Ø§Øª

0.14

locks

0.14

ples

0.14

lopedia

0.14

âĶĺ

0.14

Activations Density 0.000%

connecting words and phrases that indicate causality or relationships in the context of information and explanations

No Comments

No Known Activations