INDEX

Explanations

phrases or words that indicate the importance or role of something in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oque

-0.16

phem

-0.15

loquent

-0.15

Î´ÎŃ

-0.15

-fw

-0.15

rvÃ©

-0.14

pled

-0.14

/by

-0.14

pone

-0.14

æĨ

-0.14

POSITIVE LOGITS

0.16

uye

0.15

ize

0.14

mente

0.14

enthal

0.14

unden

0.14

udas

0.14

uchar

0.14

alsa

0.14

Activations Density 0.005%

phrases or words that indicate the importance or role of something in a specific context

No Comments

No Known Activations