INDEX

Explanations

words related to the process of evaluating or assessing something

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

åŃĺäºİ

-0.15

_NR

-0.15

Ĭ

-0.14

iap

-0.14

locker

-0.14

crease

-0.14

paque

-0.14

thouse

-0.13

 Pods

-0.13

Ŀ

-0.13

POSITIVE LOGITS

emme

0.14

 premises

0.14

uto

0.13

zes

0.13

ergic

0.13

mun

0.13

cant

0.13

tel

0.13

 deal

0.13

ide

0.13

Activations Density 0.332%

words related to the process of evaluating or assessing something

No Comments

No Known Activations