INDEX

Explanations

identifiers or numerical references likely associated with research articles or data sets

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

aise

-0.19

fusion

-0.16

 Brill

-0.15

aina

-0.15

uggy

-0.15

or

-0.14

estate

-0.14

 Williamson

-0.14

iglia

-0.14

/update

-0.14

POSITIVE LOGITS

.scalablytyped

0.17

edImage

0.17

ableObject

0.15

/antlr

0.15

iper

0.14

cek

0.14

:Object

0.14

skb

0.14

Occurred

0.14

ÑĪÐµÐ»

0.14

Activations Density 0.005%

identifiers or numerical references likely associated with research articles or data sets

No Comments

No Known Activations