INDEX

Explanations

announcements and updates regarding health and legal matters

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

cmds

-0.18

ende

-0.15

exe

-0.15

cene

-0.15

ocom

-0.14

calar

-0.13

imen

-0.13

ost

-0.13

stand

-0.13

Har

-0.13

POSITIVE LOGITS

.ManyToMany

0.15

 ÙĥØ³

0.14

 offsetof

0.14

chio

0.14

_INCLUDED

0.14

Ø¹Ø§

0.14

.IT

0.13

 labore

0.13

ÐºÑĢÐ°

0.13

dete

0.13

Activations Density 0.573%

announcements and updates regarding health and legal matters

No Comments

No Known Activations