INDEX

Explanations

words associated with medical or scientific terminology, especially in relation to processes and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ville

-0.42

son

-0.38

-0.36

-0.34

ss

-0.32

sson

-0.31

vik

-0.31

-0.30

ry

-0.30

POSITIVE LOGITS

ger

0.17

tera

0.17

ter

0.16

TER

0.15

tere

0.15

riad

0.14

etrofit

0.14

tern

0.14

ØªØ§

0.14

tero

0.14

Activations Density 0.174%

words associated with medical or scientific terminology, especially in relation to processes and conditions

No Comments

No Known Activations