INDEX

Explanations

phrases related to finding or providing information or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

RIES

-0.16

ÐµÑı

-0.15

 Excell

-0.15

,strlen

-0.14

Pri

-0.14

Kem

-0.14

agraph

-0.14

INY

-0.14

izr

-0.13

.choice

-0.13

POSITIVE LOGITS

 anytime

0.20

oler

0.19

à¹Ħà¸Ķ

0.19

 à¹Ħà¸Ķ

0.15

force

0.15

cdc

0.15

con

0.15

imulator

0.15

 easily

0.15

odiac

0.15

Activations Density 0.066%

phrases related to finding or providing information or resources

No Comments

No Known Activations