INDEX

Explanations

references to "reading" and associated activities or concepts related to literacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

sten

-0.17

ck

-0.16

ats

-0.16

ped

-0.15

ated

-0.15

oc

-0.15

iv

-0.15

 FactoryBot

-0.15

iling

-0.14

udad

-0.14

POSITIVE LOGITS

/view

0.26

/list

0.25

just

0.24

/watch

0.22

 comprehension

0.22

mitted

0.20

/w

0.19

iness

0.19

/write

0.18

 aloud

0.18

Activations Density 0.061%

references to "reading" and associated activities or concepts related to literacy

No Comments

No Known Activations