INDEX

Explanations

references to searching or discovering something

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

ugar

-0.18

.flink

-0.15

ãĥ³ãĥĲ

-0.15

aÃ±a

-0.15

chedulers

-0.15

-0.14

.AddParameter

-0.14

unden

-0.14

rello

-0.14

POSITIVE LOGITS

ache

0.17

 Cool

0.16

mand

0.16

DELETE

0.15

 Berger

0.14

 Richards

0.14

haf

0.14

 å·

0.14

 cool

0.14

Activations Density 0.001%

references to searching or discovering something

No Comments

No Known Activations