INDEX

Explanations

numerical and bibliographic references related to people and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 hardcoded

-0.17

 âĢª

-0.16

opolitan

-0.15

 Init

-0.15

essler

-0.14

ìĿ´ìŀĲ

-0.14

///

-0.14

–

-0.14

era

-0.14

<<

-0.14

POSITIVE LOGITS

$MESS

0.17

GuidId

0.15

jez

0.15

.updateDynamic

0.15

ascus

0.15

-addons

0.14

Sources

0.14

(Adapter

0.14

ableViewController

0.14

$__

0.14

Activations Density 0.028%

numerical and bibliographic references related to people and events

No Comments

No Known Activations