INDEX

Explanations

identifiers or numerical values associated with specific products or features

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

amburger

-0.15

oods

-0.15

HEET

-0.14

agna

-0.14

ongo

-0.14

rescia

-0.14

edis

-0.14

Î¹ÎºÎ·

-0.14

ÄĻd

-0.14

ÏĦÎ¶

-0.14

POSITIVE LOGITS

0.14

ãĥ©ãĥ³ãĥī

0.14

lek

0.14

 Allan

0.13

æµª

0.13

../../../../

0.13

 opener

0.13

LoadIdentity

0.13

à¥įà¤Łà¤°

0.13

Activations Density 0.013%

identifiers or numerical values associated with specific products or features

No Comments

No Known Activations