INDEX

Explanations

programming language keywords and constructs related to data manipulation and streaming operations

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

onso

-0.17

à¹Īà¸ĩ

-0.16

andas

-0.15

niÄį

-0.15

ky

-0.15

yal

-0.14

Ð»Ñİ

-0.14

AMP

-0.14

sop

-0.14

kus

-0.14

POSITIVE LOGITS

AAD

0.17

ahir

0.17

_$_

0.15

QM

0.15

.rl

0.15

å«

0.14

Ã¶l

0.14

ÏĦÎ¹Î½

0.14

Activations Density 0.001%

programming language keywords and constructs related to data manipulation and streaming operations

No Comments

No Known Activations