INDEX

Explanations

references to local and regional contexts

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

ulp

-0.16

alytics

-0.16

asename

-0.15

lick

-0.14

liste

-0.14

emic

-0.14

bare

-0.14

ÙĨØ§ÙħÙĩ

-0.14

APPLE

-0.14

ecta

-0.14

POSITIVE LOGITS

ities

0.24

/global

0.19

vore

0.17

/local

0.17

izing

0.16

ephir

0.16

-born

0.16

izedName

0.16

ised

0.16

-global

0.15

Activations Density 0.038%

references to local and regional contexts

No Comments

No Known Activations