INDEX

Explanations

terms related to DNA and its processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

gres

-0.17

pton

-0.17

amina

-0.16

uter

-0.16

ì§Ģê°Ģ

-0.16

ennes

-0.15

hall

-0.15

prav

-0.15

awe

-0.15

alls

-0.15

POSITIVE LOGITS

/pro

0.22

 Damage

0.22

/R

0.20

hel

0.19

se

0.19

 damage

0.19

 sequencing

0.18

 sequence

0.18

 sequences

0.18

sequence

0.17

Activations Density 0.015%

terms related to DNA and its processes

No Comments

No Known Activations