INDEX

Explanations

references to academic journals and research articles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

athering

-0.16

ather

-0.16

adu

-0.15

ett

-0.14

lene

-0.13

æ®ĭ

-0.13

Sat

-0.13

_LL

-0.13

Sym

-0.13

_impl

-0.13

POSITIVE LOGITS

 FindObjectOfType

0.16

ovah

0.15

aned

0.15

pekt

0.15

ProgressHUD

0.14

iskey

0.14

 dirent

0.14

/goto

0.14

wcs

0.14

neh

0.14

Activations Density 0.008%

references to academic journals and research articles

No Comments

No Known Activations