INDEX

Explanations

references to large quantities, particularly numerical values and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

á»±c

-0.15

ardo

-0.15

_INTR

-0.14

Ä±ndÄ±r

-0.14

ãģªãģĹ

-0.14

Ranges

-0.14

ranges

-0.14

 percentages

-0.14

ÄĻ

-0.13

eil

-0.13

POSITIVE LOGITS

-plus

0.24

 fewer

0.21

 unique

0.21

/-

0.21

 souls

0.20

 acres

0.20

-strong

0.20

ths

0.20

 square

0.18

sq

0.18

Activations Density 0.089%

references to large quantities, particularly numerical values and their contexts

No Comments

No Known Activations