INDEX

Explanations

terms related to drugs and their effects on health and dependence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

kor

-0.15

iets

-0.15

apur

-0.14

prak

-0.14

ãĥªãĥ¼ãĤº

-0.14

alon

-0.14

lass

-0.13

æ¨

-0.13

 Erot

-0.13

iona

-0.13

POSITIVE LOGITS

0.15

hsi

0.15

noc

0.14

 Casc

0.14

urations

0.14

Ð»ÐµÐ¼ÐµÐ½ÑĤ

0.13

oned

0.13

emies

0.13

Activations Density 1.371%

terms related to drugs and their effects on health and dependence

No Comments

No Known Activations