INDEX

Explanations

mathematical and scientific terms or parameters related to data analysis

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

cott

-0.17

 baud

-0.15

:↵↵↵↵↵↵

-0.15

anguages

-0.15

ulen

-0.14

ãĤĩ

-0.14

ElementException

-0.14

.addElement

-0.14

ombres

-0.14

uzzi

-0.14

POSITIVE LOGITS

ks

0.16

.ht

0.16

0.15

eks

0.15

0.14

Activations Density 0.120%

mathematical and scientific terms or parameters related to data analysis

No Comments

No Known Activations