INDEX

Explanations

references to significant events or actions, particularly in a social or community context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

fang

-0.16

Tru

-0.15

 instance

-0.15

 handic

-0.14

 Madison

-0.14

fan

-0.14

dds

-0.14

ett

-0.13

uem

-0.13

etre

-0.13

POSITIVE LOGITS

ektor

0.17

aver

0.16

.kr

0.15

ipa

0.15

_ioctl

0.14

JNI

0.14

 benefici

0.14

opup

0.14

itlement

0.14

agini

0.14

Activations Density 0.059%

references to significant events or actions, particularly in a social or community context

No Comments

No Known Activations