INDEX

Explanations

technical terms and syntax related to XML or file paths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 prest

-0.15

akhir

-0.15

artial

-0.15

ocate

-0.15

Ð°ÑĢÐ¾Ð´

-0.15

yal

-0.14

 Wenger

-0.14

lendir

-0.14

lier

-0.14

POSITIVE LOGITS

0.24

inha

0.22

alan

0.22

0.21

slt

0.19

SSF

0.19

ilinx

0.19

ournal

0.18

ampp

0.18

lsx

0.18

Activations Density 0.016%

technical terms and syntax related to XML or file paths

No Comments

No Known Activations