INDEX

Explanations

expressions related to numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

à¥įà¤¸à¤°

-0.15

exact

-0.15

pile

-0.14

ERA

-0.14

 exact

-0.14

 swapped

-0.14

ctal

-0.14

 frogs

-0.13

 Exact

-0.13

annes

-0.13

POSITIVE LOGITS

riel

0.18

gni

0.14

rie

0.14

eczy

0.14

gent

0.14

tery

0.14

ugi

0.14

pow

0.14

iguiente

0.14

pow

0.14

Activations Density 0.001%

expressions related to numerical data or statistics

No Comments

No Known Activations