INDEX

Explanations

references to conditions or factors that vary or depend on specific circumstances

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

zes

-0.19

ermann

-0.15

zek

-0.15

 Trend

-0.15

lod

-0.14

æīĢæľī

-0.14

abra

-0.14

chen

-0.14

ISMATCH

-0.14

Xia

-0.14

POSITIVE LOGITS

 whether

0.28

whether

0.23

 circumstances

0.23

 type

0.22

 circumstance

0.20

age

0.19

Whether

0.19

 Whether

0.18

æĺ¯åĲ¦

0.18

chosen

0.18

Activations Density 0.080%

references to conditions or factors that vary or depend on specific circumstances

No Comments

No Known Activations