INDEX

Explanations

constructs and references related to names and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.16

inha

-0.15

Mahon

-0.15

ropa

-0.15

reate

-0.14

haus

-0.14

 part

-0.14

corp

-0.14

ding

-0.14

POSITIVE LOGITS

Î±Î¹

0.15

ÑĥÑĤÐ¸

0.14

Ø®ÛĮ

0.14

ethyst

0.14

 Spiel

0.14

esc

0.13

 Wolfe

0.13

.DisplayMember

0.13

 NEGLIGENCE

0.13

etur

0.13

Activations Density 0.013%

constructs and references related to names and identifiers

No Comments

No Known Activations