INDEX

Explanations

frequent references to the government

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

 Ø²Ùħ

-0.15

Ã¶m

-0.15

ses

-0.15

 Char

-0.14

uzzi

-0.14

ãĥ¬ãĥ¼

-0.14

ety

-0.14

ETY

-0.14

vier

-0.14

emann

-0.14

POSITIVE LOGITS

.scalablytyped

0.15

 ÙģÙī

0.15

tvrt

0.14

quivo

0.14

/modal

0.14

ÄĽle

0.14

achsen

0.13

ErrorMsg

0.13

Activations Density 0.006%

frequent references to the government

No Comments

No Known Activations