INDEX

Explanations

elements related to progression and advancement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iec

-0.15

bsp

-0.15

å¿«éĢŁ

-0.14

&R

-0.14

ÏĦÏī

-0.14

egl

-0.14

ifo

-0.14

eks

-0.14

Instantiate

-0.13

amerate

-0.13

POSITIVE LOGITS

 taken

0.30

 further

0.29

 takes

0.28

 pushed

0.28

 take

0.27

 push

0.25

 Take

0.25

 Taken

0.25

takes

0.24

 Takes

0.24

Activations Density 0.140%

elements related to progression and advancement in various contexts

No Comments

No Known Activations