INDEX

Explanations

terms related to invitations and invites

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

çİ²

-0.17

-0.16

alers

-0.15

oser

-0.15

.BorderFactory

-0.14

reff

-0.14

chers

-0.14

eren

-0.14

Äħd

-0.14

lesai

-0.14

POSITIVE LOGITS

ëŀĮ

0.17

 invited

0.15

 invitation

0.15

ÄĽst

0.15

Coins

0.15

ense

0.14

ongs

0.14

ewe

0.14

ENCED

0.14

GRAM

0.14

Activations Density 0.022%

terms related to invitations and invites

No Comments

No Known Activations