INDEX

Explanations

references to specific medical conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

LTR

-0.16

ulong

-0.15

ãĥ¥

-0.15

oving

-0.14

ipple

-0.14

ocha

-0.14

vol

-0.14

.Ma

-0.14

StringBuilder

-0.14

 Kumar

-0.13

POSITIVE LOGITS

orsk

0.16

Î³Ïī

0.16

arus

0.15

RAIN

0.15

 Carbon

0.15

ucz

0.14

acak

0.14

 carbon

0.14

tip

0.14

Carbon

0.14

Activations Density 0.170%

references to specific medical conditions and treatments

No Comments

No Known Activations