INDEX

Explanations

terms related to concussions and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

OMPI

-0.16

leans

-0.15

rado

-0.15

 ÑĩÐ°

-0.14

ÐµÐ½Ð·

-0.14

tte

-0.14

uhe

-0.14

UTO

-0.14

 Venez

-0.14

AtPath

-0.13

POSITIVE LOGITS

 concussion

0.39

conc

0.35

 conc

0.35

 Conc

0.32

 brain

0.30

 Brain

0.29

 brains

0.27

brain

0.26

Brain

0.26

 helmets

0.25

Activations Density 0.042%

terms related to concussions and their effects

No Comments

No Known Activations