INDEX

Explanations

phrases and terms associated with academic content or educational institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÐµÑģÑĤÐ²

-0.13

venir

-0.12

ÏĦÎ®

-0.12

ÑıÐ»

-0.12

Å¸

-0.12

{{{

-0.12

Ð¸ÑģÐ»Ð¾Ð²

-0.11

lopedia

-0.11

arged

-0.11

.currentThread

-0.11

POSITIVE LOGITS

enie

0.16

oho

0.14

omu

0.14

 seins

0.14

 roman

0.13

eni

0.13

à¤¾:

0.13

ohana

0.13

ruz

0.12

 erotische

0.12

Activations Density 0.278%

phrases and terms associated with academic content or educational institutions

No Comments

No Known Activations