INDEX

Explanations

terms related to health care and mental health issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

itis

-0.17

uyu

-0.17

ialect

-0.17

atrix

-0.16

hythm

-0.14

ipelines

-0.14

hiro

-0.14

phan

-0.13

relude

-0.13

abbo

-0.13

POSITIVE LOGITS

fully

0.20

fulness

0.17

mate

0.17

Ø§ÙĦØ©

0.16

canf

0.15

odge

0.15

lever

0.14

rÃ¡l

0.14

Č

0.14

lice

0.14

Activations Density 0.047%

terms related to health care and mental health issues

No Comments

No Known Activations