INDEX

Explanations

instances of the word "pop" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

onna

-0.16

ÑĴ

-0.16

enton

-0.15

éĻ¢

-0.15

cury

-0.15

ort

-0.15

Ã¤nd

-0.15

 Ð½Ð°Ð²

-0.15

Ã²ng

-0.14

Ø³ÙĪ

-0.14

POSITIVE LOGITS

.DropTable

0.14

ILLE

0.14

:animated

0.14

_VENDOR

0.14

-minus

0.13

LAR

0.13

Bye

0.13

etim

0.13

jeme

0.13

 Kens

0.13

Activations Density 0.020%

instances of the word "pop" and its variations

No Comments

No Known Activations