INDEX

Explanations

instances of the term "Sans" and expressions of magnitude or significance related to size

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

falls

-0.15

gap

-0.15

endif

-0.15

ulen

-0.15

hole

-0.14

 Jerome

-0.14

´Ģ

-0.14

CAT

-0.14

 AttributeError

-0.13

ÑĤ

-0.13

POSITIVE LOGITS

vu

0.16

iams

0.16

ICA

0.15

-pt

0.15

ÐºÐ°Ð²

0.15

usra

0.14

pth

0.14

ipple

0.14

ipt

0.14

Activations Density 0.009%

instances of the term "Sans" and expressions of magnitude or significance related to size

No Comments

No Known Activations