INDEX

Explanations

proper nouns and terms related to science and mathematics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

cheid

-0.15

ucer

-0.15

ãĥĭãĥ¼

-0.15

itesi

-0.14

Ð»Ð¸Ð¶

-0.14

Ø·ÙĦ

-0.13

dera

-0.13

 Isle

-0.13

 INLINE

-0.13

 Ø¯ÙĨÛĮ

-0.13

POSITIVE LOGITS

ian

0.91

ians

0.76

IAN

0.65

ain

0.51

Ian

0.49

à¤¿à¤¯à¤¨

0.47

iana

0.47

iant

0.44

ains

0.43

rian

0.43

Activations Density 0.072%

proper nouns and terms related to science and mathematics

No Comments

No Known Activations