INDEX

Explanations

content related to job roles and hiring processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ä±s

-0.15

oba

-0.15

unta

-0.14

ÑĩÐµÐ¼

-0.14

 tá»¥

-0.14

Ù¾Ø³

-0.14

Ø´Øª

-0.14

wat

-0.14

Ð¶Ñĥ

-0.14

oldem

-0.13

POSITIVE LOGITS

asty

0.16

isci

0.15

enty

0.15

hen

0.14

 Trend

0.14

jan

0.14

And

0.14

 à¹Ĩ

0.14

egg

0.14

 Trem

0.14

Activations Density 0.110%

content related to job roles and hiring processes

No Comments

No Known Activations