INDEX

Explanations

instances of discovery or realization

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

Negative Logits

Ã©rica

-0.16

èĢ

-0.15

loquent

-0.14

/Dk

-0.14

lop

-0.14

íĴ

-0.14

éº»

-0.14

langs

-0.14

 hann

-0.13

äººãģ¯

-0.13

POSITIVE LOGITS

icas

0.15

ÑĶÐ¼

0.15

 peÄį

0.15

owell

0.14

 Fact

0.14

irut

0.14

rops

0.14

 Schwe

0.13

mere

0.13

Activations Density 0.120%

instances of discovery or realization

No Known Activations