INDEX

Explanations

references to totality or completeness

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

ALL

-0.17

 Hang

-0.15

proved

-0.14

uur

-0.14

ables

-0.14

oker

-0.14

ova

-0.14

ke

-0.14

ool

-0.14

/Math

-0.14

POSITIVE LOGITS

heart

0.18

iddi

0.17

lot

0.16

LY

0.16

section

0.15

cio

0.15

fully

0.15

Lots

0.14

 section

0.14

Activations Density 0.021%

references to totality or completeness

No Comments

No Known Activations