INDEX

Explanations

terms related to quantity and manufacturing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

aceous

-0.16

jal

-0.16

shi

-0.16

bero

-0.16

eous

-0.15

ÑģÑĮ

-0.15

(s

-0.15

umer

-0.15

EMPLARY

-0.15

izabeth

-0.15

POSITIVE LOGITS

(es

0.55

0.43

0.34

ers

0.31

iness

0.28

ingly

0.27

sing

0.27

ses

0.27

erman

0.26

es

0.26

Activations Density 0.160%

terms related to quantity and manufacturing processes

No Comments

No Known Activations