INDEX

Explanations

references to durations of time, specifically those associated with hours and their multiple usages in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

oin

-0.17

ycz

-0.15

roe

-0.15

ooter

-0.14

heck

-0.14

Cah

-0.14

 Length

-0.13

Ã¼ck

-0.13

OUCH

-0.13

à¸ĩ

-0.13

POSITIVE LOGITS

oston

0.15

ĥn

0.15

oute

0.15

Ð¸ÑĤÐ¾Ð¼

0.15

ä¸Ńæĸĩ

0.15

izons

0.14

.struts

0.14

.orange

0.14

eru

0.14

qui

0.14

Activations Density 0.007%

references to durations of time, specifically those associated with hours and their multiple usages in various contexts

No Comments

No Known Activations