INDEX

Explanations

terms related to imitation and simulation

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

rd

-0.15

ilon

-0.15

ÑĢ

-0.15

alus

-0.15

ach

-0.15

ugen

-0.15

ipp

-0.14

ened

-0.14

eron

-0.14

elic

-0.14

POSITIVE LOGITS

/mock

0.17

 Cove

0.17

/cop

0.16

imli

0.15

onto

0.15

 Claw

0.15

 exact

0.14

clr

0.14

Activations Density 0.062%

terms related to imitation and simulation

No Comments

No Known Activations