INDEX

Explanations

references to missing persons and related circumstances

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

ambre

-0.16

ÐĶÐļ

-0.14

alia

-0.14

ÑģÑĤÐ¾ÑĢ

-0.14

ouch

-0.14

/INFO

-0.14

anded

-0.14

à¥Ĥà¤²

-0.14

bourg

-0.14

YLE

-0.14

POSITIVE LOGITS

 missing

0.29

 disappearance

0.27

 Missing

0.26

Missing

0.26

 MISSING

0.24

missing

0.23

 disappeared

0.23

 disappear

0.23

_missing

0.20

 disappe

0.19

Activations Density 0.185%

references to missing persons and related circumstances

No Comments

No Known Activations