INDEX

Explanations

terms associated with health conditions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

nen

-0.14

 trai

-0.14

dle

-0.14

quer

-0.14

yst

-0.13

 rarity

-0.13

iez

-0.13

elor

-0.13

quez

-0.13

Riv

-0.13

POSITIVE LOGITS

vyk

0.17

LOAT

0.16

 Ones

0.16

traction

0.15

OURS

0.15

ultipart

0.14

 individuals

0.14

Ã³ng

0.14

.fhir

0.14

Activations Density 0.294%

terms associated with health conditions and their implications

No Comments

No Known Activations