INDEX

Explanations

phrases related to disabilities and accessibility needs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

asca

-0.16

 Wrath

-0.15

afa

-0.15

venth

-0.14

 Loving

-0.14

der

-0.14

eder

-0.14

ertz

-0.14

-0.13

ched

-0.13

POSITIVE LOGITS

oland

0.16

interrupt

0.16

EventListener

0.15

senal

0.15

arro

0.14

annes

0.14

Ø§ÙĤÙĦ

0.14

apult

0.13

ìĤ¼

0.13

tam

0.13

Activations Density 0.031%

phrases related to disabilities and accessibility needs

No Comments

No Known Activations