INDEX

Explanations

references to medical conditions, particularly cancer-related terms and their various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Äĥr

-0.16

 instead

-0.16

ellen

-0.16

ULA

-0.16

 ëĵ

-0.16

/el

-0.15

ellan

-0.15

egg

-0.15

ula

-0.15

arter

-0.14

POSITIVE LOGITS

ewed

0.20

-ex

0.20

ew

0.19

ex

0.17

Ex

0.17

ez

0.17

 Evans

0.16

EX

0.16

-extra

0.16

EX

0.16

Activations Density 0.025%

references to medical conditions, particularly cancer-related terms and their various forms

No Comments

No Known Activations

references to medical conditions, particularly cancer-related terms and their various forms

No Comments

No Known Activations