INDEX

Explanations

classifications of drugs and their relationships to specific families or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

reeze

-0.16

 Guarantee

-0.16

athom

-0.15

 guarantee

-0.14

 disappointment

-0.14

eon

-0.14

rrha

-0.14

Ð¼ÐµÑĪ

-0.13

Vul

-0.13

iasm

-0.13

POSITIVE LOGITS

quals

0.16

 category

0.16

 camp

0.16

ãĥªãĥ³

0.16

ackle

0.15

 Category

0.15

edo

0.14

uncio

0.14

.openg

0.14

lington

0.13

Activations Density 0.121%

classifications of drugs and their relationships to specific families or groups

No Comments

No Known Activations