INDEX

Explanations

keywords and acronyms that represent organizations, programs, or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ples

-0.16

Ŀi

-0.14

Ä±

-0.14

htar

-0.14

orelease

-0.14

paragus

-0.13

IRC

-0.13

Äįel

-0.13

Circular

-0.13

.osgi

-0.13

POSITIVE LOGITS

eken

0.16

stime

0.16

eyh

0.15

İ

0.15

ŀæĢ§

0.14

Fur

0.14

adays

0.14

Ð¾ÑĤÑĢÐµÐ±

0.14

etheless

0.14

Ã¡lo

0.13

Activations Density 0.420%

keywords and acronyms that represent organizations, programs, or initiatives

No Comments

No Known Activations