INDEX

Explanations

text that highlights personal relationships and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

isu

-0.17

 "(\<

-0.17

ãģĵãĤĵãģ«ãģ¡ãģ¯

-0.15

 Ø³Ùģ

-0.15

ichert

-0.15

STYPE

-0.14

ivet

-0.14

arging

-0.14

serter

-0.14

è¦§

-0.14

POSITIVE LOGITS

Dr

0.38

 Professor

0.32

Dr

0.31

Mr

0.31

Mr

0.27

Professor

0.26

 Prof

0.25

 Senator

0.25

 Judge

0.24

Ms

0.24

Activations Density 0.350%

text that highlights personal relationships and social interactions

No Comments

No Known Activations