INDEX

Explanations

references to historical events and narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ancode

-0.17

_inches

-0.17

phia

-0.16

ANGLES

-0.15

simulate

-0.15

 æ©

-0.15

á»ĳi

-0.14

 Leak

-0.14

imiter

-0.14

 Bent

-0.14

POSITIVE LOGITS

 History

0.22

 history

0.21

åı²

0.20

 historian

0.19

History

0.19

 historians

0.19

 Maiden

0.18

 hist

0.18

(hist

0.17

 Geschichte

0.17

Activations Density 0.098%

references to historical events and narratives

No Comments

No Known Activations