INDEX

Explanations

references to significant moments or objects in a narrative context

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

Ð¾Ð»ÐµÑĤ

-0.17

-0.16

ÂĽ

-0.14

éĺµ

-0.14

Ð°Ð½Ð¾Ð²

-0.13

 åĮ

-0.13

 åĿ

-0.13

-Sah

-0.13

 tinh

-0.13

POSITIVE LOGITS

kou

0.15

 progress

0.15

usta

0.14

IFA

0.14

erd

0.14

ihat

0.14

emmel

0.14

 Tire

0.13

 process

0.13

.getBoundingClientRect

0.13

Activations Density 0.262%

references to significant moments or objects in a narrative context

No Comments

No Known Activations