INDEX

Explanations

negative phrases or expressions, particularly those indicating a disagreement or rejection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Jarvis

-0.17

land

-0.16

onen

-0.15

ÐµÐ¼Ð°

-0.14

rego

-0.14

tright

-0.14

omore

-0.13

.IContainer

-0.13

tractor

-0.13

 Cast

-0.13

POSITIVE LOGITS

ÐµÑĦ

0.17

åĢī

0.15

Ã¹

0.14

Nit

0.14

_NV

0.14

EventListener

0.14

’na

0.13

 Thickness

0.13

Ñĭ

0.13

Activations Density 0.215%

negative phrases or expressions, particularly those indicating a disagreement or rejection

No Comments

No Known Activations