INDEX

Explanations

terms related to stochastic processes and randomness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

aub

-0.16

 Bender

-0.16

ocket

-0.15

ynchron

-0.15

/footer

-0.14

ÐµÐºÑĤÐ¾ÑĢÐ°

-0.14

/umd

-0.14

isms

-0.14

 Ã¡n

-0.14

beck

-0.14

POSITIVE LOGITS

lick

0.16

OP

0.15

Tech

0.14

icity

0.14

 nowhere

0.14

Ð»Ð¸Ð²

0.14

illaume

0.14

LayoutPanel

0.13

Kent

0.13

assi

0.13

Activations Density 0.049%

terms related to stochastic processes and randomness

No Comments

No Known Activations