INDEX

Explanations

technical jargon related to data structures and messaging frameworks

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

atron

-0.17

 Muham

-0.16

itez

-0.16

ilim

-0.15

iju

-0.15

meden

-0.15

 Baghd

-0.15

mlink

-0.14

"display

-0.14

ayd

-0.14

POSITIVE LOGITS

 bits

0.21

bits

0.21

 shift

0.20

field

0.19

 shifts

0.19

bit

0.18

(bits

0.17

 shifting

0.17

Bit

0.17

ä½į

0.16

Activations Density 0.037%

technical jargon related to data structures and messaging frameworks

No Comments

No Known Activations