INDEX

Explanations

phrases related to measurements and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ilib

-0.16

rop

-0.14

çģµ

-0.14

abee

-0.14

ato

-0.14

oup

-0.14

spir

-0.14

 /*č↵

-0.13

ugas

-0.13

 strokeLine

-0.13

POSITIVE LOGITS

odon

0.15

-ng

0.15

enet

0.14

beit

0.14

ç£¨

0.14

 BÃ¶l

0.13

é¦

0.13

 Bubble

0.13

 Avec

0.13

Meg

0.13

Activations Density 0.637%

phrases related to measurements and statistics

No Comments

No Known Activations