INDEX

Explanations

references to digital applications and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

antage

-0.15

flu

-0.15

ieres

-0.14

PU

-0.14

 Moms

-0.14

çŀ

-0.14

reta

-0.14

/process

-0.14

doch

-0.14

ansom

-0.14

POSITIVE LOGITS

klÃ¤

0.15

dij

0.15

.sell

0.15

anon

0.14

ToJson

0.14

 Chow

0.14

imity

0.14

proxy

0.14

ucc

0.14

Activations Density 0.140%

references to digital applications and their functionalities

No Comments

No Known Activations