INDEX

Explanations

punctuation marks, particularly periods and commas

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

 BigNumber

-0.16

 ActionTypes

-0.15

ague

-0.14

Rue

-0.14

æĿ¡

-0.14

Ľ°

-0.14

è¾Ĩ

-0.13

onda

-0.13

vie

-0.13

ied

-0.13

POSITIVE LOGITS

hower

0.18

edb

0.17

zelf

0.17

nbsp

0.16

plode

0.16

ed

0.16

apons

0.15

DTV

0.15

anine

0.15

Î»Î¹Î¬

0.15

Activations Density 0.071%

punctuation marks, particularly periods and commas

No Comments

No Known Activations