INDEX

Explanations

numerical data and quantifiers related to statistics and percentages

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ifu

-0.15

azzi

-0.15

ÑĨÑĭ

-0.14

ãĥ¼ãĥŀ

-0.14

 Bulletin

-0.14

oble

-0.14

Î¹ÎºÎ¿

-0.13

emas

-0.13

ŀ

-0.13

Ð¦

-0.13

POSITIVE LOGITS

Statics

0.15

 zastup

0.14

rag

0.14

ÙĦÙĬÙģ

0.14

_UNDEF

0.14

andReturn

0.14

æħĭ

0.14

ä½³

0.13

isson

0.13

ood

0.13

Activations Density 0.161%

numerical data and quantifiers related to statistics and percentages

No Comments

No Known Activations

numerical data and quantifiers related to statistics and percentages

No Comments

No Known Activations