INDEX

Explanations

boolean conditions and statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

seed

-0.15

iders

-0.14

tingham

-0.14

åºķ

-0.14

ushman

-0.14

isors

-0.14

ãĥ³ãĥī

-0.14

 tall

-0.14

anik

-0.13

POSITIVE LOGITS

.opend

0.17

jedn

0.17

etrics

0.17

ews

0.16

enge

0.16

orida

0.15

TOTYPE

0.15

ODB

0.14

Equivalent

0.14

Activations Density 0.047%

boolean conditions and statements

No Comments

No Known Activations