INDEX

Explanations

references to news media and interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.14

ass

-0.14

ena

-0.14

fp

-0.14

Cas

-0.14

 Carr

-0.14

Seg

-0.14

oe

-0.14

ought

-0.14

MEA

-0.13

POSITIVE LOGITS

addir

0.18

ixed

0.17

 Roose

0.16

.scalablytyped

0.16

Ð´Ð¸Ð½

0.15

 refr

0.15

ixo

0.15

Ð»Ð°Ð²

0.14

letal

0.14

ucz

0.14

Activations Density 0.150%

references to news media and interviews

No Comments

No Known Activations