INDEX

Explanations

specific noun phrases related to product names and models

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

.scalablytyped

-0.15

ÙĪÛĮÙĦ

-0.14

zek

-0.14

.ease

-0.14

eler

-0.14

hq

-0.14

urette

-0.13

wan

-0.13

 Tham

-0.13

comb

-0.13

POSITIVE LOGITS

/portfolio

0.15

¨

0.14

VERSE

0.14

 Gates

0.14

ammu

0.13

elli

0.13

unde

0.13

.Components

0.13

 gates

0.13

atics

0.13

Activations Density 0.021%

specific noun phrases related to product names and models

No Comments

No Known Activations