INDEX

Explanations

phrases indicating quantifiable relationships or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

olidays

-0.15

Ø§Ø¦Ùħ

-0.15

/views

-0.14

uld

-0.14

chooser

-0.14

lier

-0.14

ues

-0.13

±

-0.13

innacle

-0.13

 Prelude

-0.13

POSITIVE LOGITS

 things

0.18

 main

0.17

 slic

0.15

 reasons

0.15

 thing

0.15

yms

0.14

rna

0.14

abis

0.14

obi

0.14

 those

0.13

Activations Density 0.026%

phrases indicating quantifiable relationships or comparisons

No Comments

No Known Activations