INDEX

Explanations

technical terms and expressions related to mathematical and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

æľĽ

-0.15

æķ

-0.14

éļ

-0.14

Ef

-0.14

itize

-0.13

áº

-0.13

agoon

-0.13

cco

-0.13

 Pert

-0.13

lyn

-0.13

POSITIVE LOGITS

ses

0.15

isinde

0.15

ixa

0.15

ÌĨ

0.14

.Sdk

0.14

 ÃĩaÄŁ

0.14

imas

0.14

criptor

0.13

pekt

0.13

acias

0.13

Activations Density 0.935%

technical terms and expressions related to mathematical and scientific contexts

No Comments

No Known Activations