INDEX

Explanations

references to programming languages and system-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ister

-0.18

ocl

-0.15

anne

-0.15

annes

-0.15

shaw

-0.14

ist

-0.14

ake

-0.14

ews

-0.13

iston

-0.13

Keys

-0.13

POSITIVE LOGITS

aml

0.15

à¹Ģà¸Ľà¸Ńà¸£

0.15

eline

0.15

RIA

0.14

.apple

0.14

rose

0.14

 Verg

0.13

.Restr

0.13

ERGY

0.13

 mobil

0.13

Activations Density 0.003%

references to programming languages and system-related terms

No Comments

No Known Activations