INDEX

Explanations

references to algebraic concepts and terminology

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

cas

-0.18

lass

-0.15

 vibr

-0.15

HasForeignKey

-0.14

ijing

-0.14

bib

-0.14

Hack

-0.14

 Hack

-0.14

iÃ³

-0.14

cie

-0.14

POSITIVE LOGITS

oyal

0.17

 PropertyValue

0.15

lero

0.15

undle

0.15

licable

0.15

udent

0.15

trand

0.14

otics

0.14

IFT

0.14

Ã¶g

0.14

Activations Density 0.004%

references to algebraic concepts and terminology

No Comments

No Known Activations