INDEX

Explanations

references to graphics processing units (GPUs) and related technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 electr

-0.17

imei

-0.17

brero

-0.15

_minor

-0.15

æ±½

-0.14

alian

-0.14

uess

-0.14

 elektrik

-0.14

lectric

-0.14

ios

-0.14

POSITIVE LOGITS

 Perf

0.16

 Wing

0.14

 discrete

0.14

ãĥ³ãĤ¹

0.14

 perf

0.14

KEN

0.14

 wing

0.14

riendly

0.14

 Wolf

0.14

Cry

0.14

Activations Density 0.010%

references to graphics processing units (GPUs) and related technologies

No Comments

No Known Activations