INDEX

Explanations

references to medical conditions, treatments, or drug-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ace

-0.26

achel

-0.25

-ac

-0.25

abil

-0.24

AA

-0.24

ACH

-0.24

Ð°Ð±

-0.24

-ab

-0.24

ach

-0.24

aal

-0.23

POSITIVE LOGITS

ANTI

0.17

arch

0.17

 Antique

0.17

Ð°Ð½ÑĤÐ°Ð¶

0.17

angu

0.16

apesh

0.16

archives

0.16

Argentina

0.16

 antiqu

0.16

arge

0.16

Activations Density 0.032%

references to medical conditions, treatments, or drug-related information

No Comments

No Known Activations