INDEX

Explanations

negative sentiments or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Ãªm

-0.17

uze

-0.16

semicolon

-0.15

berman

-0.15

Ã¸d

-0.15

ÐºÐ¸Ð½

-0.14

æ¶

-0.14

«ng

-0.13

_<

-0.13

quired

-0.13

POSITIVE LOGITS

0.30

0.28

0.23

0.21

0.19

0.18

-'

0.18

Activations Density 0.021%

negative sentiments or outcomes

No Comments

No Known Activations