INDEX

Explanations

proper nouns, particularly names and places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

urt

-0.15

icans

-0.15

è¾ĳ

-0.15

(class

-0.14

 Matth

-0.14

ism

-0.14

terior

-0.14

atern

-0.13

ÃŃ

-0.13

urgeon

-0.13

POSITIVE LOGITS

urette

0.16

Å¡ov

0.16

intr

0.16

ÑĢÐ¾ÑĪ

0.15

Ã¤ge

0.15

shore

0.15

ÑĢÐ¾Ð¶

0.14

aget

0.14

ÑĥÐ²

0.14

APA

0.13

Activations Density 0.033%

proper nouns, particularly names and places

No Comments

No Known Activations