INDEX

Explanations

terms related to various fields of science

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

dden

-0.17

izabeth

-0.17

gang

-0.16

-urlencoded

-0.15

ARRANT

-0.15

abinet

-0.15

ingham

-0.15

aign

-0.15

altar

-0.14

alamat

-0.14

POSITIVE LOGITS

otti

0.15

uels

0.15

Gaw

0.15

Nu

0.15

ÅĻen

0.15

ÐºÐ°Ð²

0.15

ottes

0.15

cname

0.14

 prompt

0.14

wich

0.14

Activations Density 0.022%

terms related to various fields of science

No Comments

No Known Activations