INDEX

Explanations

phrases related to specific historical contexts or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

(æľĪ

-0.15

ilib

-0.15

oha

-0.14

 ëħĦëıĦë³Ħ

-0.13

.idea

-0.13

Ø®Ø±Ø§Ø¬

-0.13

otten

-0.13

oq

-0.13

osaic

-0.13

amon

-0.13

POSITIVE LOGITS

 late

0.62

late

0.52

mid

0.46

 early

0.44

 Late

0.42

Late

0.40

early

0.39

mid

0.30

nin

0.29

’

0.29

Activations Density 0.110%

phrases related to specific historical contexts or events

No Comments

No Known Activations

phrases related to specific historical contexts or events

No Comments

No Known Activations