INDEX

Explanations

terms related to viruses and viral infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dalton

-0.15

nÃ©

-0.15

inar

-0.15

-ÑĤÐ°ÐºÐ¸

-0.15

isman

-0.15

lander

-0.15

eur

-0.14

anon

-0.14

cene

-0.14

POSITIVE LOGITS

sher

0.17

udeau

0.17

rst

0.16

Ãĺ

0.15

amaz

0.14

 demanding

0.14

ombat

0.14

qua

0.14

nd

0.14

airo

0.14

Activations Density 0.015%

terms related to viruses and viral infections

No Comments

No Known Activations