INDEX

Explanations

phrases related to programming concepts and ease of use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Hast

-0.15

.ReadAll

-0.15

 hast

-0.15

 gÃ¼

-0.15

ody

-0.14

adesh

-0.14

 anchor

-0.13

Kr

-0.13

ombat

-0.13

çį²

-0.13

POSITIVE LOGITS

avin

0.17

antar

0.17

Collapsed

0.15

iom

0.14

otland

0.14

ward

0.14

.FontStyle

0.14

gnore

0.14

 maintain

0.14

Ø§ÙĪÙĨØ¯

0.14

Activations Density 0.153%

phrases related to programming concepts and ease of use

No Comments

No Known Activations