INDEX

Explanations

phrases that indicate a form of dependency or connection to something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ourt

-0.19

 parole

-0.16

rak

-0.15

orge

-0.14

alley

-0.14

ucc

-0.14

ÅĻik

-0.14

 Lama

-0.14

ipay

-0.14

raig

-0.14

POSITIVE LOGITS

mith

0.15

æ°ı

0.15

-sort

0.14

 semi

0.14

icular

0.14

semi

0.14

hood

0.14

å¸¸

0.14

emics

0.14

owell

0.14

Activations Density 0.049%

phrases that indicate a form of dependency or connection to something

No Comments

No Known Activations