INDEX

Explanations

phrases that indicate searching for specific items or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

thers

-0.15

_rq

-0.15

_ABI

-0.14

æµľ

-0.14

uest

-0.14

 Comfort

-0.14

izados

-0.14

asta

-0.14

POSITIVE LOGITS

Appear

0.15

kup

0.15

aar

0.14

aan

0.14

LinkId

0.14

_INCLUDED

0.14

.IContainer

0.13

zan

0.13

opyright

0.13

link

0.13

Activations Density 0.061%

phrases that indicate searching for specific items or services

No Comments

No Known Activations