INDEX

Explanations

terms related to cytokines and lymphocyte classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

azzi

-0.17

 Hosp

-0.16

.ib

-0.14

asin

-0.14

 tert

-0.14

 Ventura

-0.14

suc

-0.14

 Salon

-0.13

 vinc

-0.13

 familiar

-0.13

POSITIVE LOGITS

 mole

0.19

 Angiosper

0.18

Ø§Ø³Ø·Ø©

0.16

agra

0.16

ÙĦÙĥØªØ±

0.15

nelle

0.14

itler

0.14

 Overflow

0.14

 krist

0.14

 Koch

0.14

Activations Density 0.106%

terms related to cytokines and lymphocyte classification

No Comments

No Known Activations