INDEX

Explanations

variations of the word "divine" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

yl

-0.15

UNE

-0.15

 Peripheral

-0.14

untas

-0.14

ycop

-0.14

aly

-0.14

edio

-0.14

ungen

-0.13

 peripheral

-0.13

ONY

-0.13

POSITIVE LOGITS

apr

0.17

0.15

ohana

0.15

Fault

0.14

oce

0.14

apl

0.14

 Forgotten

0.14

plash

0.14

ÑĤÐ°Ð»

0.14

Activations Density 0.025%

variations of the word "divine" and its related forms

No Comments

No Known Activations