INDEX

Explanations

phrases related to case studies and their outcomes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ham

-0.16

uite

-0.15

 interpol

-0.14

chia

-0.14

etter

-0.13

vl

-0.13

baum

-0.13

lices

-0.13

ku

-0.13

hiba

-0.13

POSITIVE LOGITS

esis

0.17

DEX

0.16

 przypad

0.15

ÏīÎ½Î±

0.14

createClass

0.14

edException

0.14

emmel

0.14

[section

0.14

uzz

0.14

ÐŀÐł

0.14

Activations Density 0.137%

phrases related to case studies and their outcomes

No Known Activations