INDEX

Explanations

questions that start with "how."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

é£¯

-0.16

pole

-0.15

uely

-0.15

uhan

-0.14

nable

-0.14

oard

-0.14

 hakk

-0.13

orphic

-0.13

borg

-0.13

ified

-0.13

POSITIVE LOGITS

itzer

0.21

soever

0.20

beit

0.17

lessness

0.17

arth

0.16

zu

0.16

atts

0.15

TestFixture

0.14

oping

0.14

 cada

0.14

Activations Density 0.098%

questions that start with "how."

No Comments

No Known Activations