INDEX

Explanations

references to finality or last occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

coles

-0.16

æľĢæĸ°

-0.16

heimer

-0.15

abajo

-0.15

.vs

-0.15

aar

-0.15

.nextSibling

-0.15

acer

-0.15

.nextElement

-0.15

lets

-0.14

POSITIVE LOGITS

 before

0.28

 remaining

0.27

gas

0.25

hur

0.24

 Remaining

0.23

remaining

0.23

 Before

0.23

-before

0.23

before

0.22

_before

0.21

Activations Density 0.075%

references to finality or last occurrences

No Comments

No Known Activations