INDEX

Explanations

phrases indicating destinations or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

acente

-0.16

oun

-0.15

ONGO

-0.15

ReadStream

-0.14

ething

-0.14

anya

-0.14

onya

-0.14

uese

-0.13

ãģªãģĮ

-0.13

POSITIVE LOGITS

 sunny

0.16

 site

0.15

 destinations

0.15

ilog

0.15

see

0.15

 places

0.15

 warmer

0.15

empt

0.15

 rendez

0.14

 visit

0.14

Activations Density 0.092%

phrases indicating destinations or locations

No Comments

No Known Activations