INDEX

Explanations

references to a specific software company or its products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ambre

-0.17

''''

-0.16

 Hyper

-0.16

quate

-0.14

ium

-0.14

 Macro

-0.14

CPP

-0.14

aru

-0.14

 bottoms

-0.14

essional

-0.14

POSITIVE LOGITS

spl

0.23

Spl

0.18

unk

0.17

Spl

0.17

endid

0.17

UNK

0.17

enic

0.17

ÏĥÎ¹Î±

0.16

éª

0.16

Ã¼gen

0.16

Activations Density 0.009%

references to a specific software company or its products

No Comments

No Known Activations