INDEX

Explanations

the presence of parentheses and punctuation indicating a conversational or reflective tone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.16

play

-0.15

ist

-0.14

Escort

-0.14

ke

-0.14

ac

-0.14

ç¹

-0.14

etti

-0.13

ing

-0.13

POSITIVE LOGITS

Qualifier

0.15

æ£ĭçīĮ

0.15

æķ¦

0.14

rello

0.14

gettext

0.14

.ld

0.14

_inches

0.14

undef

0.14

cak

0.14

tual

0.14

Activations Density 0.137%

the presence of parentheses and punctuation indicating a conversational or reflective tone

No Comments

No Known Activations