INDEX

Explanations

instances of the word "with," indicating a focus on relationships or associations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ogy

-0.18

hed

-0.16

yp

-0.15

Ð¾ÐºÐµ

-0.15

loff

-0.15

à¸²à¸ģà¸£

-0.14

hydration

-0.14

_GRE

-0.14

aten

-0.14

essen

-0.14

POSITIVE LOGITS

elas

0.16

ANDOM

0.16

=msg

0.15

dÃŃ

0.15

aines

0.15

ands

0.15

}elseif

0.14

elize

0.14

ãĥ

0.14

athers

0.14

Activations Density 0.069%

instances of the word "with," indicating a focus on relationships or associations in the text

No Comments

No Known Activations