INDEX

Explanations

words and terms related to medical conditions or symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

es

-0.19

eson

-0.17

esch

-0.17

elli

-0.16

emer

-0.16

eln

-0.16

esc

-0.16

tir

-0.16

tro

-0.15

estro

-0.15

POSITIVE LOGITS

trasound

0.23

monary

0.21

terior

0.21

áº·ng

0.20

tras

0.20

iflower

0.18

thood

0.17

icrous

0.17

ÃŃÅĻ

0.17

icious

0.16

Activations Density 0.042%

words and terms related to medical conditions or symptoms

No Comments

No Known Activations