INDEX

Explanations

key identifiers, classifications, and features related to products or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

idebar

-0.14

æľīåħ³

-0.14

jsp

-0.13

prak

-0.13

aed

-0.13

avra

-0.13

 Ð½ÐµÑİ

-0.12

.hu

-0.12

 overall

-0.12

imilar

-0.12

POSITIVE LOGITS

 finally

0.16

âĢª

0.15

istrovstvÃŃ

0.15

 zwarte

0.13

 hopefully

0.13

-native

0.13

ï¸ı

0.13

finally

0.13

áº¯ng

0.13

ETO

0.12

Activations Density 0.018%

key identifiers, classifications, and features related to products or concepts

No Comments

No Known Activations

key identifiers, classifications, and features related to products or concepts

No Comments

No Known Activations