INDEX

Explanations

phrases and keywords related to references, specifics, or structured data in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ð¾Ð·Ð¸

-0.16

ãĥ¯ãĤ¤ãĥĪ

-0.12

ozilla

-0.12

Dud

-0.12

Ìģ

-0.12

 Affero

-0.12

bucks

-0.12

ëį°ìĿ´íĬ¸

-0.12

imbledon

-0.12

engers

-0.12

POSITIVE LOGITS

phia

0.14

ãĥ¼ãĥ«

0.13

itm

0.13

hower

0.13

.scalablytyped

0.13

InternalServerError

0.13

fabs

0.13

:numel

0.13

Fade

0.13

Msp

0.12

Activations Density 0.008%

phrases and keywords related to references, specifics, or structured data in communication

No Comments

No Known Activations