INDEX

Explanations

references to the year 191, particularly in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

edy

-0.19

offs

-0.16

emens

-0.15

off

-0.15

¤í

-0.15

OrDefault

-0.15

ummings

-0.15

 ÙħØŃ

-0.14

eds

-0.14

eking

-0.14

POSITIVE LOGITS

0.20

utow

0.17

0.15

.fp

0.15

runner

0.15

/XMLSchema

0.15

aque

0.15

illet

0.14

Ø§ÙĨÙĩ

0.14

Activations Density 0.008%

references to the year 191, particularly in historical contexts

No Comments

No Known Activations