INDEX

Explanations

key moments and conclusions in stories or performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

NEXT

-0.17

 next

-0.17

_next

-0.16

¿ł

-0.15

Next

-0.15

 Next

-0.15

 early

-0.15

Early

-0.15

bis

-0.15

POSITIVE LOGITS

 tail

0.24

-final

0.21

 final

0.20

final

0.20

 Tail

0.19

Tail

0.19

.tail

0.18

orph

0.18

_tail

0.18

tail

0.17

Activations Density 0.167%

key moments and conclusions in stories or performances

No Comments

No Known Activations