INDEX

Explanations

references to specific locations or identifiers related to websites and documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

xing

-0.17

eties

-0.16

oldem

-0.16

eum

-0.15

ĭ

-0.15

ousel

-0.15

.TabStop

-0.14

etty

-0.14

ILT

-0.14

ampp

-0.14

POSITIVE LOGITS

apl

0.18

idi

0.17

0.15

ational

0.15

 Bomb

0.15

.dispatch

0.14

lesen

0.14

 dispatch

0.14

voc

0.14

aland

0.14

Activations Density 0.071%

references to specific locations or identifiers related to websites and documents

No Comments

No Known Activations