INDEX

Explanations

terms related to database configuration and viewer capabilities

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

ÑĢÐ°Ð²Ð¸

-0.16

Î½ÏĮ

-0.14

esian

-0.14

 Mister

-0.14

acios

-0.14

ESIS

-0.13

istrat

-0.13

ilden

-0.13

.circular

-0.13

_timezone

-0.13

POSITIVE LOGITS

ÑĶÐ²

0.16

vement

0.15

Subview

0.14

imd

0.14

yz

0.13

uisse

0.13

 Ð±Ð°Ð³

0.13

 terk

0.13

ismet

0.13

Activations Density 0.212%

terms related to database configuration and viewer capabilities

No Comments

No Known Activations