INDEX

Explanations

keywords and file structures related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

é¢¨

-0.17

enstein

-0.16

otto

-0.15

asis

-0.15

okt

-0.15

çıŃ

-0.14

Ð¾ÑĩÐºÐ¸

-0.14

å·¦åı³

-0.14

Ð°ÑĤÐ¾

-0.14

Fmt

-0.14

POSITIVE LOGITS

kos

0.17

trap

0.16

oltip

0.16

rega

0.16

_pel

0.14

.Physics

0.14

ÏĦÎ¹Îº

0.14

 CONSEQUENTIAL

0.14

errupt

0.14

edium

0.14

Activations Density 0.152%

keywords and file structures related to programming and software development

No Comments

No Known Activations