INDEX

Explanations

references to specific diseases or health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

UIF

-0.14

Ð²Ð¸ÑĤ

-0.14

ifikasi

-0.14

 Throw

-0.14

net

-0.14

ÑĢÐ¸Ð¼

-0.14

affer

-0.13

look

-0.13

prav

-0.13

 å®

-0.13

POSITIVE LOGITS

HasKey

0.14

ahoo

0.14

obs

0.14

âĻ¡

0.14

Unload

0.14

flater

0.13

 onDataChange

0.13

Bah

0.13

quip

0.13

Bah

0.13

Activations Density 0.021%

references to specific diseases or health conditions

No Comments

No Known Activations