INDEX

Explanations

references to a specific data processing framework and its associated terms

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

enson

-0.14

esk

-0.14

hub

-0.14

akan

-0.14

amax

-0.14

.updateDynamic

-0.14

hour

-0.14

bows

-0.14

endale

-0.13

ernes

-0.13

POSITIVE LOGITS

 security

0.18

\grid

0.17

ipa

0.17

 Security

0.16

.util

0.16

serter

0.16

util

0.15

rem

0.15

.ip

0.15

ipc

0.14

Activations Density 0.004%

references to a specific data processing framework and its associated terms

No Comments

No Known Activations