INDEX

Explanations

phrases and words associated with providing answers or responses to inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

quez

-0.18

igi

-0.16

Ì£

-0.15

ÑįÐ¹

-0.14

hammad

-0.14

ogram

-0.14

-bin

-0.14

kop

-0.14

 Rican

-0.13

ç½

-0.13

POSITIVE LOGITS

stell

0.17

idual

0.15

itol

0.15

/Instruction

0.15

ende

0.15

ported

0.14

åĽŀçŃĶ

0.14

nable

0.14

 questions

0.13

fortawesome

0.13

Activations Density 0.042%

phrases and words associated with providing answers or responses to inquiries

No Comments

No Known Activations