INDEX

Explanations

statistical terms and analysis related to experimental data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

rad

-0.15

xfc

-0.15

pen

-0.15

oard

-0.14

upro

-0.14

 ÑĢÐ°Ð´

-0.14

 sens

-0.14

zej

-0.14

foy

-0.14

 bubbles

-0.14

POSITIVE LOGITS

 ÙĩØ¯

0.15

Bea

0.15

ollen

0.14

å¡

0.14

 prere

0.14

Rub

0.14

allet

0.13

ÑĥÑĩÐ°Ñģ

0.13

éĢĶ

0.13

::*

0.13

Activations Density 0.223%

statistical terms and analysis related to experimental data

No Comments

No Known Activations