INDEX

Explanations

document structure elements and metadata related to media or archival content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 consenting

-0.15

olist

-0.15

 archives

-0.15

annies

-0.14

orias

-0.14

ëĭĿ

-0.14

ÐµÑģ

-0.14

 èĹ

-0.14

archive

-0.14

impan

-0.14

POSITIVE LOGITS

LC

0.19

LOC

0.19

LOC

0.17

rado

0.17

LC

0.17

(ca

0.16

ados

0.15

DLC

0.15

LOT

0.15

ddy

0.15

Activations Density 0.008%

document structure elements and metadata related to media or archival content

No Comments

No Known Activations