INDEX

Explanations

phrases that indicate expressing thanks or invitations to engage

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

awi

-0.17

CommandEvent

-0.16

Ð¸Ð²ÑĪÐ¸

-0.15

 awakeFromNib

-0.15

éĻµ

-0.14

CEED

-0.14

aina

-0.14

flen

-0.14

ByVersion

-0.14

.setdefault

-0.14

POSITIVE LOGITS

erde

0.15

 Scre

0.15

oe

0.15

 apart

0.15

rie

0.14

 declarations

0.14

 Bernard

0.14

ambil

0.13

och

0.13

 Alexander

0.13

Activations Density 0.019%

phrases that indicate expressing thanks or invitations to engage

No Comments

No Known Activations