INDEX

Explanations

phrases indicating conditions or exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ffer

-0.16

jal

-0.15

je

-0.13

ouse

-0.13

enis

-0.13

TON

-0.13

aday

-0.13

inou

-0.13

ataka

-0.13

zan

-0.13

POSITIVE LOGITS

/un

0.15

Â·Â·

0.14

 necessarily

0.14

rames

0.13

 necessary

0.13

ky

0.13

Ã¡du

0.13

 else

0.13

ãĥŃãĥ³

0.13

ICAST

0.13

Activations Density 0.015%

phrases indicating conditions or exceptions

No Comments

No Known Activations