INDEX

Explanations

references to geographical locations or administrative divisions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

.scalablytyped

-0.16

 Hole

-0.15

Attached

-0.15

OwnProperty

-0.14

/bower

-0.14

TRL

-0.14

Attachment

-0.14

 Dalton

-0.14

emin

-0.14

erval

-0.14

POSITIVE LOGITS

 Commission

0.14

 Gregg

0.14

itet

0.14

EGIN

0.14

egas

0.14

 Pang

0.14

ContextHolder

0.14

UIScrollView

0.14

 commission

0.13

zon

0.13

Activations Density 0.026%

references to geographical locations or administrative divisions

No Comments

No Known Activations