INDEX

Explanations

references to actions, particularly related to physical activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

pher

-0.18

afil

-0.17

shint

-0.16

ulmuÅŁ

-0.16

atedRoute

-0.15

ÑİÑĤ

-0.15

DSA

-0.15

erdem

-0.15

atte

-0.15

 navigationOptions

-0.14

POSITIVE LOGITS

ìĬ¬

0.16

Ras

0.15

 Maur

0.15

 grades

0.14

ory

0.14

ew

0.14

oh

0.14

ÑĢÐ°Ñĩ

0.14

 crossed

0.13

 Bere

0.13

Activations Density 0.209%

references to actions, particularly related to physical activities or events

No Comments

No Known Activations