INDEX

Explanations

instructions and requests related to programming or updating statuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 eventdata

-0.15

-0.14

 ÎķÎº

-0.14

-0.13

rays

-0.13

pu

-0.13

 Cooke

-0.13

fort

-0.13

Ĩ

-0.13

POSITIVE LOGITS

OMPI

0.18

roe

0.16

Maker

0.15

taire

0.15

efon

0.14

ufen

0.14

itution

0.14

seau

0.14

áºŃp

0.14

omba

0.14

Activations Density 0.083%

instructions and requests related to programming or updating statuses

No Comments

No Known Activations