INDEX

Explanations

variations of the word "encounter."

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

reo

-0.17

gart

-0.17

acey

-0.16

keley

-0.15

acco

-0.15

rega

-0.15

JB

-0.14

jn

-0.14

fully

-0.14

wort

-0.14

POSITIVE LOGITS

hort

0.20

ires

0.16

emble

0.16

odi

0.14

eti

0.14

Ĩ

0.14

ird

0.14

abay

0.14

lesia

0.14

ConverterFactory

0.14

Activations Density 0.013%

variations of the word "encounter."

No Comments

No Known Activations