INDEX

Explanations

phrases indicating availability and variety of products or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ombre

-0.16

soever

-0.15

iegel

-0.15

ÏĦÎ¹Îº

-0.15

eus

-0.14

 maman

-0.14

bum

-0.14

ÑĪÐµÐ²

-0.14

 Aware

-0.14

ycin

-0.14

POSITIVE LOGITS

eny

0.16

ynet

0.16

Sk

0.15

enet

0.15

0.14

areth

0.14

isko

0.14

vaÅ¾

0.14

 kÃŃch

0.14

 Holl

0.13

Activations Density 0.037%

phrases indicating availability and variety of products or options

No Comments

No Known Activations