INDEX

Explanations

references to health-related terms and anatomy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Lawson

-0.15

 stag

-0.14

¡

-0.14

 tone

-0.14

ild

-0.14

Äįi

-0.14

ocket

-0.13

---

-0.13

/Instruction

-0.13

POSITIVE LOGITS

ysa

0.16

.uc

0.16

 Aires

0.15

muz

0.15

toi

0.14

ears

0.14

osate

0.14

ëłµ

0.14

Brush

0.14

esiz

0.14

Activations Density 0.308%

references to health-related terms and anatomy

No Comments

No Known Activations