INDEX

Explanations

terms and phrases associated with substance abuse and forensic analysis of intoxication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ocha

-0.15

ampie

-0.15

 premature

-0.14

uml

-0.14

 Dumpster

-0.14

'gc

-0.14

ehler

-0.14

erea

-0.14

 prematurely

-0.14

Nd

-0.13

POSITIVE LOGITS

ilim

0.16

hower

0.16

Bid

0.15

uppercase

0.15

sob

0.15

SI

0.15

kad

0.14

ÏģÎ¹Î¬

0.14

bid

0.14

abay

0.14

Activations Density 0.205%

terms and phrases associated with substance abuse and forensic analysis of intoxication

No Comments

No Known Activations