INDEX

Explanations

references to time periods following significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

etrize

-0.17

legg

-0.16

Ì£

-0.16

enler

-0.15

ittle

-0.15

Ã¼tÃ¼n

-0.15

Ð²Ð°Ð½

-0.14

.AttributeSet

-0.14

yon

-0.14

leness

-0.14

POSITIVE LOGITS

alle

0.17

 spot

0.15

Tou

0.14

lier

0.14

 Christ

0.14

 Henderson

0.14

 Spot

0.13

 Bass

0.13

 Pepper

0.13

Activations Density 0.019%

references to time periods following significant events

No Comments

No Known Activations