INDEX

Explanations

terms related to agreements and formal declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

"crypto

-0.17

tics

-0.15

ÑĳÐ¼

-0.14

Ð¾Ð²Ð¾ÑĢ

-0.14

iT

-0.14

à¤°à¤£

-0.14

iros

-0.14

peaker

-0.14

gom

-0.14

ä¼Ļ

-0.14

POSITIVE LOGITS

que

0.19

orum

0.18

 Laurent

0.17

Sty

0.17

vel

0.17

um

0.16

atum

0.16

modo

0.16

yla

0.16

 pattern

0.15

Activations Density 0.070%

terms related to agreements and formal declarations

No Comments

No Known Activations