INDEX

Explanations

phrases and expressions that indicate transitions or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uze

-0.18

zÃŃ

-0.17

ersive

-0.16

engu

-0.15

ugins

-0.15

odes

-0.15

_READONLY

-0.15

ÙģØ³

-0.15

fsp

-0.15

tÃ©

-0.15

POSITIVE LOGITS

 rally

0.15

ola

0.14

 Rally

0.14

Reload

0.14

ARGS

0.14

é¥

0.13

ito

0.13

intColor

0.13

_factors

0.13

iesel

0.13

Activations Density 0.002%

phrases and expressions that indicate transitions or comparisons

No Comments

No Known Activations