INDEX

Explanations

instructions and descriptions related to physical positioning and arrangement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lict

-0.16

 Branch

-0.15

obox

-0.15

 Blonde

-0.15

am

-0.15

omba

-0.14

Kou

-0.14

POSITIVE LOGITS

 orientation

0.38

 orientations

0.35

 Orientation

0.35

orientation

0.32

Orientation

0.30

 orient

0.27

 Orient

0.26

_orientation

0.26

orient

0.26

 facing

0.25

Activations Density 0.168%

instructions and descriptions related to physical positioning and arrangement

No Comments

No Known Activations