INDEX

Explanations

references to databases and data management concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ifter

-0.20

rema

-0.18

ibern

-0.17

İ·

-0.16

amas

-0.16

sx

-0.15

ool

-0.14

å¡ļ

-0.14

ashboard

-0.14

ninger

-0.14

POSITIVE LOGITS

pedia

0.20

\Eloquent

0.20

coin

0.18

AndView

0.17

pole

0.16

ÚĨÙĩ

0.15

olt

0.15

ms

0.15

!=(

0.14

ple

0.14

Activations Density 0.041%

references to databases and data management concepts

No Comments

No Known Activations