INDEX

Explanations

words and phrases related to entertainment and media in a mixed-language context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

æ¹

-0.17

Ð°Ð»ÐµÐ¶

-0.16

grass

-0.14

yd

-0.14

ym

-0.14

heg

-0.13

ãĤĥ

-0.13

ãĤĴè¦ĭãĤĭ

-0.13

.ci

-0.13

reg

-0.13

POSITIVE LOGITS

à¸§à¸¥

0.15

uae

0.15

èĦ

0.14

icari

0.14

uka

0.14

á»¥

0.14

Ear

0.14

á»ĳ

0.14

çİĩ

0.14

asmus

0.13

Activations Density 0.111%

words and phrases related to entertainment and media in a mixed-language context

No Comments

No Known Activations