INDEX

Explanations

key attributes, including names, data points, and significant metrics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Flush

-0.16

 Charter

-0.15

Kis

-0.15

 Mane

-0.14

oksen

-0.14

stras

-0.14

-fl

-0.14

OrFail

-0.14

Flush

-0.14

abella

-0.14

POSITIVE LOGITS

0.16

Vir

0.16

ussels

0.16

vir

0.15

engan

0.15

ells

0.14

Vir

0.14

loh

0.14

vir

0.14

cre

0.14

Activations Density 0.046%

key attributes, including names, data points, and significant metrics in various contexts

No Comments

No Known Activations