INDEX

Explanations

significant mentions of guidelines or recommendations in a context related to health or research

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

oyer

-0.16

acas

-0.16

sted

-0.15

lop

-0.15

IClient

-0.15

allah

-0.15

oten

-0.15

esser

-0.14

tras

-0.14

aten

-0.14

POSITIVE LOGITS

å®Ĺ

0.17

.GroupLayout

0.15

atoi

0.15

 æ¹

0.15

 Alloc

0.15

eyse

0.15

YLON

0.14

ernet

0.14

 Dart

0.14

AA

0.14

Activations Density 0.015%

significant mentions of guidelines or recommendations in a context related to health or research

No Comments

No Known Activations