INDEX

Explanations

geographical and political entities within 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 @ 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

 Lore

-0.16

Jog

-0.15

utton

-0.15

SEL

-0.14

 adipiscing

-0.14

 ration

-0.14

 River

-0.13

emand

-0.13

unts

-0.13

POSITIVE LOGITS

ODEV

0.16

vil

0.16

ycz

0.15

idis

0.15

/Dk

0.14

asÄ±ndan

0.14

lid

0.14

@qq

0.14

/System

0.14

UBLE

0.14

Activations Density 0.274%

geographical and political entities within the text

No Comments

No Known Activations