INDEX

Explanations

occurrences of the word "och" and variations of the word "it."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÑĥÑĢÑĥ

-0.15

eken

-0.15

Ã¦k

-0.14

Ã¸d

-0.14

 ########.

-0.14

inos

-0.14

/lg

-0.14

agar

-0.14

eki

-0.14

uckland

-0.13

POSITIVE LOGITS

itan

0.16

vit

0.15

 nonatomic

0.14

plural

0.14

exe

0.14

ogany

0.14

ember

0.14

isch

0.14

itic

0.13

Activations Density 0.000%

occurrences of the word "och" and variations of the word "it."

No Comments

No Known Activations