INDEX

Explanations

references to "Master" or related terms indicating advanced academic degrees or qualifications

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

_parallel

-0.18

Parallel

-0.15

Ð¼ÐµÐ»ÑĮ

-0.15

ateur

-0.15

Ð»Ð¸ÑĨ

-0.15

Ã´ng

-0.15

 Guys

-0.14

run

-0.14

andan

-0.14

parallel

-0.14

POSITIVE LOGITS

LAR

0.19

0.18

ãĥ£

0.16

YM

0.15

hips

0.14

å¯¸

0.14

inae

0.14

ÐºÐ¾Ð²Ð¾

0.14

ous

0.14

amp

0.14

Activations Density 0.006%

references to "Master" or related terms indicating advanced academic degrees or qualifications

No Comments

No Known Activations