INDEX

Explanations

references to processes or methods in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ower

-0.17

gether

-0.17

ìłĢ

-0.16

xca

-0.15

cup

-0.15

umph

-0.14

verage

-0.14

ITS

-0.14

_fetch

-0.13

.scrollHeight

-0.13

POSITIVE LOGITS

eses

0.17

ess

0.16

allet

0.16

iot

0.16

DAQ

0.15

yb

0.15

WD

0.14

ariat

0.14

sut

0.14

 piger

0.13

Activations Density 0.022%

references to processes or methods in code

No Comments

No Known Activations