INDEX

Explanations

expressions indicating conditions or relationships affecting individuals

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

cot

-0.18

VT

-0.16

andes

-0.15

iless

-0.15

VT

-0.15

onian

-0.14

UA

-0.14

äºĭåĭĻ

-0.14

wit

-0.14

BF

-0.14

POSITIVE LOGITS

 priv

0.16

/***/

0.15

oss

0.15

 Priv

0.14

ingham

0.14

 handjob

0.14

.va

0.14

ynam

0.13

adem

0.13

egie

0.13

Activations Density 0.000%

expressions indicating conditions or relationships affecting individuals

No Comments

No Known Activations

expressions indicating conditions or relationships affecting individuals

No Comments

No Known Activations