INDEX

Explanations

specific technical terms related to scientific and medical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ushman

-0.17

iles

-0.16

odes

-0.15

èĤ¡

-0.15

assi

-0.15

owie

-0.14

ILES

-0.14

 Sphere

-0.14

lesi

-0.14

chwitz

-0.14

POSITIVE LOGITS

ardown

0.18

uke

0.17

igos

0.15

uner

0.15

 Pent

0.15

AMERA

0.14

rub

0.14

onz

0.14

 GlobalKey

0.14

cola

0.14

Activations Density 0.007%

specific technical terms related to scientific and medical information

No Comments

No Known Activations