INDEX

Explanations

references to formal communication, such as letters and interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

abet

-0.15

rary

-0.15

 Ð´ÐµÐ»Ðµ

-0.14

áº«n

-0.14

ÐµÐ³ÑĢÐ°

-0.13

elin

-0.13

.Trace

-0.13

 komple

-0.13

perature

-0.13

 Ð¿ÑĢÐ°Ð²Ð°

-0.13

POSITIVE LOGITS

 statement

0.28

 speech

0.27

speech

0.24

 interview

0.24

 statements

0.22

Speech

0.22

 visit

0.20

 Speech

0.19

 letter

0.19

 Statement

0.19

Activations Density 0.083%

references to formal communication, such as letters and interviews

No Comments

No Known Activations

references to formal communication, such as letters and interviews

No Comments

No Known Activations