INDEX

Explanations

words related to reduction and minimizing impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.17

agua

-0.15

virt

-0.15

olis

-0.15

.rpm

-0.15

lio

-0.14

strup

-0.14

 altogether

-0.13

ATA

-0.13

POSITIVE LOGITS

'gc

0.17

asmus

0.15

/null

0.15

-HT

0.15

hof

0.15

ado

0.14

ongan

0.14

arin

0.14

/free

0.14

 Mayer

0.14

Activations Density 0.028%

words related to reduction and minimizing impact

No Comments

No Known Activations