INDEX

Explanations

technical terms and jargon related to specific disciplines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rex

-0.18

orthy

-0.15

zsche

-0.15

à¹Ĭ

-0.15

iland

-0.15

iales

-0.14

pix

-0.14

 suff

-0.14

tras

-0.14

ilis

-0.14

POSITIVE LOGITS

0.14

 Abed

0.14

CHA

0.13

VERR

0.13

 heirs

0.13

 overhead

0.13

 offen

0.13

exion

0.13

).__

0.12

 Swan

0.12

Activations Density 0.007%

technical terms and jargon related to specific disciplines

No Comments

No Known Activations