INDEX

Explanations

date and time formats, particularly in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

cribed

-0.17

 tane

-0.16

lege

-0.15

ore

-0.15

-0.14

gia

-0.14

èĺ

-0.14

asz

-0.14

.mx

-0.14

èį

-0.13

POSITIVE LOGITS

anka

0.16

aupt

0.15

utoff

0.15

 çķĻ

0.14

ITTE

0.14

pard

0.14

voie

0.14

hop

0.14

Ã¼nchen

0.13

logan

0.13

Activations Density 0.026%

date and time formats, particularly in programming contexts

No Comments

No Known Activations