INDEX

Explanations

references to locations named "Cape."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ODEV

-0.17

czy

-0.17

¯u

-0.15

nan

-0.14

ëĿ½

-0.13

tant

-0.13

ees

-0.13

APS

-0.13

mitt

-0.13

ertain

-0.13

POSITIVE LOGITS

 Verde

0.28

Cod

0.26

Cod

0.21

 Wrath

0.21

Bre

0.20

cod

0.19

 Town

0.18

 Fear

0.18

Gir

0.17

COD

0.17

Activations Density 0.004%

references to locations named "Cape."

No Comments

No Known Activations