INDEX

Explanations

terms related to concussions and their effects on health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 needle

-0.15

ipple

-0.15

egt

-0.14

egin

-0.14

needle

-0.14

ranking

-0.14

kre

-0.14

ãĥ©ãĤ¹

-0.14

illes

-0.14

Neighbors

-0.13

POSITIVE LOGITS

 concussion

0.35

conc

0.29

 Conc

0.28

 conc

0.25

 Brain

0.24

 brain

0.23

brain

0.21

 brains

0.21

Brain

0.20

 head

0.20

Activations Density 0.043%

terms related to concussions and their effects on health

No Comments

No Known Activations