INDEX

Explanations

references to awards and recognition in the context of individuals' achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

thread

-0.16

engin

-0.15

sez

-0.15

.grad

-0.14

diz

-0.14

 faults

-0.14

à¥ģà¤¬

-0.14

çŁ¢

-0.14

 thread

-0.14

fault

-0.14

POSITIVE LOGITS

Mc

0.23

Mc

0.20

McD

0.19

(mc

0.18

 McDonald

0.17

McL

0.17

 ÐľÐ°Ðº

0.17

McM

0.17

htdocs

0.17

Mac

0.16

Activations Density 0.027%

references to awards and recognition in the context of individuals' achievements

No Comments

No Known Activations