INDEX

Explanations

words related to specialized vocabulary and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

cred

-0.16

wat

-0.15

Î´Î±

-0.15

ouch

-0.14

esso

-0.14

eso

-0.14

vale

-0.14

 ìķĦëĭĪëĿ¼

-0.14

ora

-0.14

iei

-0.14

POSITIVE LOGITS

 Ð²Ð¾Ð¹

0.16

ROADCAST

0.16

abble

0.15

uegos

0.14

ÚĨØ§Ø±

0.14

anning

0.14

klu

0.14

uchs

0.14

ake

0.14

0.13

Activations Density 0.020%

words related to specialized vocabulary and technical terms

No Comments

No Known Activations