INDEX

Explanations

instances of dialogue and emotional expressions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ĶåĽŀ

-0.14

 reversible

-0.14

ench

-0.14

 '-';↵

-0.13

/pub

-0.13

doz

-0.13

atz

-0.13

bs

-0.13

 ,↵↵

-0.13

.sz

-0.13

POSITIVE LOGITS

0.26

 "↵

0.17

'"

0.16

""

0.16

à¸±à¸Ļà¸ĺ

0.15

icker

0.15

"$

0.15

ares

0.14

".

0.14

Activations Density 0.092%

instances of dialogue and emotional expressions in the text

No Comments

No Known Activations