INDEX

Explanations

numerical rankings and sizes related to market positions and populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

pci

-0.17

itto

-0.17

eness

-0.14

Ð´Ð°Ð»

-0.14

 first

-0.14

nah

-0.14

stood

-0.13

ÐµÑĦ

-0.13

Ã©n

-0.13

iad

-0.13

POSITIVE LOGITS

-fast

0.24

-ranking

0.22

-largest

0.21

-h

0.21

-leading

0.20

 behind

0.20

-ranked

0.19

 ranked

0.19

larg

0.18

arily

0.18

Activations Density 0.015%

numerical rankings and sizes related to market positions and populations

No Comments

No Known Activations