INDEX

Explanations

punctuation marks and specific formatting elements 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

stem

-0.16

 Issue

-0.16

 Davies

-0.15

æ³ķäºº

-0.15

essen

-0.14

vÃ©

-0.14

ilent

-0.14

pri

-0.14

idea

-0.14

ehler

-0.14

POSITIVE LOGITS

uche

0.18

adero

0.16

singleton

0.16

ches

0.15

ucher

0.15

chl

0.14

edar

0.14

gies

0.14

HEME

0.13

à¸Īà¸£

0.13

Activations Density 0.060%

punctuation marks and specific formatting elements in the text

No Comments

No Known Activations