INDEX

Explanations

terms associated with health-related topics, particularly concerning viruses and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Kab

-0.17

-0.16

Py

-0.15

at

-0.15

SP

-0.14

 dist

-0.14

br

-0.14

hin

-0.14

 examples

-0.14

POSITIVE LOGITS

åıĬåħ¶

0.27

ograd

0.17

olland

0.15

atak

0.15

udad

0.15

ept

0.15

.ua

0.14

uggle

0.14

/epl

0.14

_ctor

0.14

Activations Density 0.288%

terms associated with health-related topics, particularly concerning viruses and their effects

No Comments

No Known Activations