INDEX

Explanations

numerical representations of data or measurements

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

bol

-0.16

ajar

-0.15

znik

-0.15

/cms

-0.14

olin

-0.14

orth

-0.14

aju

-0.14

ooke

-0.14

eut

-0.14

ajes

-0.14

POSITIVE LOGITS

innamon

0.16

ModelProperty

0.14

Ð¿Ð¾Ð²

0.14

ugh

0.14

arrants

0.14

Æ¡

0.14

CONN

0.13

urname

0.13

inalg

0.13

Activations Density 0.047%

numerical representations of data or measurements

No Comments

No Known Activations