INDEX

Explanations

instances of the word "all"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

eltas

-0.15

resse

-0.15

stad

-0.14

à¹ĭ

-0.14

 staat

-0.14

obbled

-0.13

inize

-0.13

 Specialty

-0.13

lassen

-0.13

	strncpy

-0.13

POSITIVE LOGITS

alah

0.17

YRO

0.15

alam

0.14

uda

0.14

-ball

0.14

nÃŃk

0.14

ippet

0.14

brick

0.13

Lac

0.13

amma

0.13

Activations Density 0.012%

instances of the word "all"

No Comments

No Known Activations