INDEX

Explanations

references to knowledge and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

\<^

-0.17

istol

-0.16

ulant

-0.16

az

-0.15

go

-0.15

ross

-0.15

/group

-0.14

otts

-0.14

bons

-0.14

shaw

-0.14

POSITIVE LOGITS

ably

0.23

fulness

0.21

fully

0.19

ledged

0.18

gable

0.17

 about

0.16

ously

0.16

 base

0.16

igne

0.15

Activations Density 0.029%

references to knowledge and understanding

No Comments

No Known Activations