INDEX

Explanations

phrases indicating exclusivity or uniqueness, particularly in relation to significance or ranking

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rove

-0.20

hani

-0.17

ucci

-0.16

BoundingClientRect

-0.14

isoft

-0.14

::$

-0.14

gne

-0.14

posal

-0.14

berman

-0.14

åģ

-0.13

POSITIVE LOGITS

ighet

0.16

nor

0.16

airs

0.15

ighton

0.15

lung

0.15

oud

0.15

gary

0.14

.Func

0.14

à¤ĸ

0.14

 nail

0.14

Activations Density 0.036%

phrases indicating exclusivity or uniqueness, particularly in relation to significance or ranking

No Comments

No Known Activations