INDEX

Explanations

terms related to scientific research and methodology, particularly in biology and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

chy

-0.17

lymp

-0.17

agraph

-0.16

ngo

-0.16

glyph

-0.16

th

-0.16

ths

-0.16

atically

-0.16

ographical

-0.16

loth

-0.16

POSITIVE LOGITS

ologia

0.24

oter

0.23

of

0.22

ologÃŃa

0.22

ografia

0.22

otec

0.21

iasi

0.21

ossil

0.19

ogen

0.19

orre

0.19

Activations Density 0.024%

terms related to scientific research and methodology, particularly in biology and data analysis

No Comments

No Known Activations