INDEX

Explanations

references to quantities of time spent on activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÌĨ

-0.17

/from

-0.16

-0.15

utm

-0.15

utas

-0.14

antan

-0.14

odelist

-0.14

bsolute

-0.14

etti

-0.14

(^

-0.13

POSITIVE LOGITS

zl

0.17

æ¬

0.17

nez

0.14

 onDataChange

0.14

zel

0.14

ãĥĥãĥģ

0.14

 rupt

0.14

amin

0.13

Î½Ïī

0.13

itzer

0.13

Activations Density 0.033%

references to quantities of time spent on activities

No Comments

No Known Activations