INDEX

Explanations

indefinite articles in various languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

wart

-0.20

ories

-0.16

lessly

-0.16

 einer

-0.15

ä¸ĢåĢĭ

-0.15

çļĦä¸Ģä¸ª

-0.15

zÃŃ

-0.15

ensitive

-0.15

-0.14

 stuff

-0.14

POSITIVE LOGITS

 certain

0.22

ione

0.21

/all

0.18

IDADE

0.18

 Certain

0.17

æĸ°çļĦ

0.16

-third

0.16

gh

0.16

iling

0.16

ida

0.15

Activations Density 0.034%

indefinite articles in various languages

No Comments

No Known Activations