INDEX

Explanations

the structure and organization of arguments or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

à¸¥à¸²à¸Ķ

-0.17

eger

-0.15

åĨł

-0.15

laz

-0.15

pez

-0.15

ëŁ

-0.15

¼åĲĪ

-0.14

Ĵ

-0.14

ÅĤÄħ

-0.14

pes

-0.14

POSITIVE LOGITS

 basically

0.35

 briefly

0.34

 Basically

0.34

 Brief

0.33

Basically

0.32

 nutshell

0.32

 brief

0.32

 summary

0.30

Brief

0.30

brief

0.29

Activations Density 0.126%

the structure and organization of arguments or narratives

No Comments

No Known Activations