INDEX

Explanations

mathematical notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Ã©al

-0.14

-ren

-0.14

ç½²

-0.13

aits

-0.13

itur

-0.13

iseum

-0.13

hai

-0.13

icros

-0.13

tle

-0.13

POSITIVE LOGITS

_{

0.19

QUOTE

0.18

Esp

0.15

ungen

0.14

ened

0.14

quot

0.14

empo

0.14

Jump

0.14

ked

0.13

ungs

0.13

Activations Density 0.038%

mathematical notation and symbols

No Comments

No Known Activations