INDEX

Explanations

specific programming code snippets and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iras

-0.19

imals

-0.18

ittle

-0.16

itas

-0.16

Segoe

-0.15

confidence

-0.15

æŁ±

-0.15

 dÃ¹

-0.14

ovna

-0.14

 trailer

-0.13

POSITIVE LOGITS

 Weston

0.15

aza

0.15

 McKenzie

0.14

efon

0.14

">//

0.14

 Dich

0.14

ynes

0.14

alez

0.14

ill

0.14

illac

0.14

Activations Density 0.063%

specific programming code snippets and related terminology

No Comments

No Known Activations