INDEX

Explanations

phrases indicating continuation or persistence over time

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

itsu

-0.17

nj

-0.15

 Phill

-0.15

ehr

-0.14

anner

-0.14

loses

-0.14

Ri

-0.14

alt

-0.14

POSITIVE LOGITS

 alive

0.47

alive

0.40

 Alive

0.34

 active

0.33

Alive

0.32

_alive

0.27

-active

0.26

 ACTIVE

0.26

active

0.26

_ACTIVE

0.26

Activations Density 0.100%

phrases indicating continuation or persistence over time

No Comments

No Known Activations