INDEX

Explanations

technical terms and components related to data storage and processing structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Goldberg

-0.17

udeau

-0.15

yi

-0.15

agar

-0.15

Nur

-0.14

nal

-0.14

ickle

-0.14

.gc

-0.14

.Binding

-0.14

Claims

-0.14

POSITIVE LOGITS

adÃŃ

0.18

iagnostics

0.15

Arb

0.15

artz

0.14

íĺ¸

0.14

ered

0.14

unting

0.14

pective

0.14

IVATE

0.14

½Ķ

0.14

Activations Density 0.012%

technical terms and components related to data storage and processing structures

No Comments

No Known Activations