INDEX

Explanations

references to dosing and dosage in medical or pharmaceutical contexts

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

ries

-0.15

hausen

-0.14

ibraries

-0.14

rip

-0.14

egers

-0.14

ashtra

-0.13

igo

-0.13

={"/

-0.13

ellas

-0.13

outedEventArgs

-0.13

POSITIVE LOGITS

oko

0.15

owe

0.14

antal

0.14

iger

0.14

ourt

0.14

gent

0.14

ãģĦãģĭ

0.14

(es

0.14

centre

0.13

gu

0.13

Activations Density 0.008%

references to dosing and dosage in medical or pharmaceutical contexts

No Comments

No Known Activations