INDEX

Explanations

references to names or titles within a specific cultural or artistic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

unal

-0.18

Wel

-0.15

ALS

-0.14

ensem

-0.14

ounge

-0.14

Vendor

-0.14

oksen

-0.14

baugh

-0.14

InputElement

-0.14

POSITIVE LOGITS

arakter

0.19

rust

0.18

mel

0.18

vat

0.17

.fhir

0.16

itin

0.16

NJ

0.16

loe

0.15

ÑĢÐ¾Ð½Ð¸ÑĩÐµÑģ

0.15

cust

0.15

Activations Density 0.008%

references to names or titles within a specific cultural or artistic context

No Comments

No Known Activations