INDEX

Explanations

terms related to injuries, hazards, and medical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

olute

-0.15

Ø±ÙĪØ¬

-0.14

ought

-0.14

<Guid

-0.14

fon

-0.14

raz

-0.13

aul

-0.13

ounty

-0.13

 samo

-0.13

à¤ľà¤°

-0.13

POSITIVE LOGITS

prit

0.17

0.16

ahl

0.16

á»ķ

0.16

wahl

0.15

essions

0.15

ãģ£ãģ¡

0.15

akter

0.15

å®¹

0.14

birthdate

0.14

Activations Density 0.209%

terms related to injuries, hazards, and medical issues

No Comments

No Known Activations