INDEX

Explanations

references to formats or types of structured data and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÏģÎ±

-0.16

inke

-0.15

azel

-0.15

indle

-0.15

>NN

-0.14

Ä±zÄ±

-0.13

quoise

-0.13

imen

-0.13

Ãºp

-0.13

consin

-0.13

POSITIVE LOGITS

Ð½Ð°Ð´Ð»ÐµÐ¶

0.14

0.13

RIPT

0.13

aren

0.13

 xÃ©t

0.12

anager

0.12

 Clement

0.12

ofstream

0.12

Gee

0.12

Activations Density 0.152%

references to formats or types of structured data and identifiers

No Comments

No Known Activations