INDEX

Explanations

terms related to various industries and current events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.18

 Wheel

-0.17

âĢ¦↵

-0.16

 âĢ¦↵

-0.16

my

-0.16

culus

-0.15

ulla

-0.15

 Lever

-0.15

ext

-0.15

POSITIVE LOGITS

.visitMethod

0.16

ÐºÐ¼

0.16

Ø¦

0.15

acha

0.15

elerik

0.15

 poil

0.14

/Runtime

0.14

Âłtom

0.14

å¥

0.13

$LANG

0.13

Activations Density 0.350%

terms related to various industries and current events

No Comments

No Known Activations