INDEX

Explanations

indicators of size and ranking among places or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.gdx

-0.18

egade

-0.16

 intermediate

-0.14

 Worst

-0.14

ernel

-0.14

umper

-0.14

etter

-0.13

urrency

-0.13

GF

-0.13

DG

-0.13

POSITIVE LOGITS

ç¬¬ä¸ī

0.15

 Holt

0.15

orphic

0.15

heits

0.15

AINS

0.14

 third

0.14

à¤¸à¤¨

0.14

omorphic

0.14

elight

0.14

zeich

0.13

Activations Density 0.066%

indicators of size and ranking among places or entities

No Comments

No Known Activations