INDEX

Explanations

punctuation marks, particularly commas and parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oras

-0.17

roll

-0.16

ncia

-0.15

 Bram

-0.15

Ð²Ð¸ÑĤ

-0.14

ksam

-0.14

ibility

-0.14

dup

-0.14

young

-0.14

axis

-0.14

POSITIVE LOGITS

esome

0.16

rÃ¡t

0.15

uent

0.15

ostÃŃ

0.15

Ø¨ÙĪØ§Ø³Ø·Ø©

0.14

ÐµÑĢÐ¶Ð°Ð²

0.14

tty

0.14

 Tmax

0.14

eyJ

0.14

bsite

0.14

Activations Density 0.000%

punctuation marks, particularly commas and parentheses

No Comments

No Known Activations