INDEX

Explanations

numerical values related to referencing sections of a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

inge

-0.16

 FIFO

-0.15

antal

-0.15

zk

-0.14

DTV

-0.14

och

-0.14

erland

-0.14

uch

-0.14

erde

-0.14

erer

-0.14

POSITIVE LOGITS

lio

0.16

<fieldset

0.14

_consts

0.14

ì§ľ

0.13

":[{↵

0.13

 assistir

0.13

_SUITE

0.13

ChildIndex

0.13

 derec

0.13

 Factor

0.13

Activations Density 0.024%

numerical values related to referencing sections of a document

No Comments

No Known Activations