INDEX

Explanations

terms related to fitness and health metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Dich

-0.16

 ApplicationException

-0.16

 Variant

-0.15

 variant

-0.15

à¥ģà¤¹

-0.15

ActionCreators

-0.15

undy

-0.15

ivor

-0.14

variant

-0.14

utta

-0.14

POSITIVE LOGITS

_bi

0.16

frey

0.16

orz

0.16

embro

0.15

unsch

0.15

kav

0.15

net

0.14

bish

0.14

lÃ¡

0.14

ekk

0.14

Activations Density 0.032%

terms related to fitness and health metrics

No Comments

No Known Activations