INDEX

Explanations

terms and concepts associated with reading and literacy education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ux

-0.16

shm

-0.16

ÅĤ

-0.15

idd

-0.14

ion

-0.14

atory

-0.14

aku

-0.14

re

-0.14

 Simon

-0.13

oin

-0.13

POSITIVE LOGITS

ãĥ¼ãĥª

0.19

riad

0.17

ombine

0.17

ÑĢÐ¾Ð·

0.15

onden

0.15

ritel

0.15

 ÐºÐ½Ð¸Ð¶

0.14

ModelProperty

0.14

pdev

0.14

istring

0.14

Activations Density 0.039%

terms and concepts associated with reading and literacy education

No Comments

No Known Activations