INDEX

Explanations

words indicating creation or production

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

GIN

-0.17

puted

-0.16

 Ð¶Ðµ

-0.16

ugin

-0.15

inkle

-0.14

ayÄ±n

-0.14

wyn

-0.14

rome

-0.14

 ateÅŁ

-0.14

rado

-0.14

POSITIVE LOGITS

it

0.20

ALLED

0.14

#ad

0.14

zew

0.14

 sense

0.13

enberg

0.13

iert

0.13

riad

0.13

amura

0.13

ossa

0.13

Activations Density 0.067%

words indicating creation or production

No Comments

No Known Activations