INDEX

Explanations

references to autoimmune regulators and antibodies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.Emit

-0.16

dera

-0.15

aspers

-0.14

è²¼

-0.14

olatile

-0.14

REDIENT

-0.13

 Davies

-0.13

è¥²

-0.13

lhs

-0.13

ÑĥÐ³

-0.13

POSITIVE LOGITS

 gene

0.36

 protein

0.35

 family

0.31

 proteins

0.30

 genes

0.28

iso

0.28

 Gene

0.25

-family

0.25

gene

0.24

hom

0.24

Activations Density 0.074%

references to autoimmune regulators and antibodies

No Comments

No Known Activations