INDEX

Explanations

terms related to health, disease, and biological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

adden

-0.14

eken

-0.14

piar

-0.14

 Willis

-0.14

ucc

-0.14

 everywhere

-0.13

 ÄĳÃ´i

-0.13

 vmax

-0.13

 correlation

-0.13

aru

-0.13

POSITIVE LOGITS

inan

0.16

idot

0.15

CREMENT

0.14

 Integral

0.14

 status

0.13

.indices

0.13

+='<

0.13

'&&

0.13

Dok

0.13

 CircularProgress

0.13

Activations Density 0.125%

terms related to health, disease, and biological conditions

No Comments

No Known Activations