INDEX

Explanations

negations or expressions of doubt and uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Wor

-0.15

Ã§i

-0.14

ÄŁ

-0.14

anÃ§a

-0.13

ylko

-0.13

Ã§ak

-0.13

Ð³Ñĥ

-0.13

.onCreate

-0.13

POSITIVE LOGITS

lisi

0.18

 (*((

0.16

è¾¼

0.15

cio

0.15

,copy

0.14

 Î±Îº

0.14

æħİ

0.14

&)↵

0.14

ESA

0.14

çµ±

0.14

Activations Density 0.074%

negations or expressions of doubt and uncertainty

No Comments

No Known Activations