INDEX

Explanations

formats and elements typical of scientific publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

è¸ı

-0.18

rz

-0.15

illis

-0.15

aison

-0.15

eson

-0.15

iana

-0.14

eme

-0.14

arde

-0.14

<::

-0.14

rane

-0.14

POSITIVE LOGITS

plash

0.15

AGR

0.14

ULL

0.14

 original

0.14

 Original

0.14

 Huck

0.14

 retr

0.14

getObject

0.14

 adul

0.14

ull

0.14

Activations Density 0.005%

formats and elements typical of scientific publications

No Comments

No Known Activations