INDEX

Explanations

references to specific pages or identifiers related to documents or files

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

enha

-0.20

jeta

-0.18

stras

-0.18

jvu

-0.16

jours

-0.15

¶Į

-0.15

uforia

-0.15

¦¬

-0.15

regnum

-0.15

orial

-0.15

POSITIVE LOGITS

Pag

0.17

pg

0.16

/pg

0.16

urus

0.15

 ReturnType

0.15

andom

0.15

oda

0.15

Pg

0.15

 Nack

0.15

ame

0.14

Activations Density 0.020%

references to specific pages or identifiers related to documents or files

No Comments

No Known Activations