INDEX

Explanations

expressions of frustration or issues with technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

enic

-0.16

claimer

-0.16

 Cousins

-0.14

 Bender

-0.14

 popular

-0.14

 Wiring

-0.13

isay

-0.13

 personally

-0.13

variants

-0.13

 perf

-0.13

POSITIVE LOGITS

olib

0.19

.getOwnProperty

0.15

ãģĹãģŁãĤī

0.14

istrovstvÃŃ

0.14

ALCHEMY

0.14

 ICON

0.14

VERS

0.14

ARCHAR

0.14

ãĥĨãĥ«

0.14

spath

0.13

Activations Density 0.146%

expressions of frustration or issues with technology

No Comments

No Known Activations