INDEX

Explanations

phrases related to visual content and its presentation

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

)((((

-0.16

 Folk

-0.15

ÎµÎ¹

-0.15

upal

-0.15

_stdio

-0.14

bia

-0.14

ngo

-0.14

Fol

-0.14

ube

-0.14

 Fabric

-0.14

POSITIVE LOGITS

emoc

0.16

andel

0.15

_emit

0.14

 å°

0.14

nist

0.14

andr

0.14

aled

0.14

anian

0.13

sek

0.13

eh

0.13

Activations Density 0.394%

phrases related to visual content and its presentation

No Comments

No Known Activations