INDEX

Explanations

specific organizational names and designations related to services or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Äįky

-0.17

utsch

-0.17

RelativeTo

-0.16

ehler

-0.16

_makeConstraints

-0.15

ZD

-0.15

auss

-0.15

.Dto

-0.14

Leaks

-0.14

/goto

-0.14

POSITIVE LOGITS

ÑĢÐ¾Ð¹

0.15

Ry

0.15

aro

0.15

ryn

0.14

errmsg

0.14

ingham

0.14

 Shed

0.14

.xx

0.14

Ald

0.14

aside

0.13

Activations Density 0.183%

specific organizational names and designations related to services or entities

No Comments

No Known Activations