INDEX

Explanations

dates and specific months mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 profiler

-0.17

 profiling

-0.16

iben

-0.15

Î»Î®

-0.15

/details

-0.14

iac

-0.14

 disturb

-0.14

quip

-0.13

aly

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.15

ÙĪÙģÙĬ

0.15

.mapbox

0.15

amba

0.15

ega

0.15

azz

0.15

 mÃ¡lo

0.15

)(__

0.14

patch

0.14

roman

0.14

Activations Density 0.060%

dates and specific months mentioned in the text

No Comments

No Known Activations