INDEX

Explanations

phrases related to access to services and resources in various contexts, particularly healthcare and education

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

opak

-0.15

imir

-0.14

 Ramsey

-0.14

obe

-0.14

stal

-0.13

proto

-0.13

 modular

-0.13

TV

-0.13

app

-0.13

Ð¾ÐºÐ¾Ð»

-0.13

POSITIVE LOGITS

teness

0.16

rost

0.14

ocale

0.14

.yy

0.14

ertia

0.14

vos

0.14

anian

0.14

ached

0.13

getManager

0.13

avax

0.13

Activations Density 0.070%

phrases related to access to services and resources in various contexts, particularly healthcare and education

No Comments

No Known Activations