INDEX

Explanations

instances of assignment operations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

umer

-0.18

UME

-0.16

erten

-0.16

æ¼«

-0.16

ollen

-0.15

 openFileDialog

-0.15

SSIP

-0.15

 Goldberg

-0.14

unt

-0.14

erts

-0.14

POSITIVE LOGITS

itoris

0.17

DefaultValue

0.16

ContentAlignment

0.15

íķĻíļĮ

0.15

ENE

0.14

sort

0.14

alus

0.14

ascal

0.14

udu

0.14

ÏĥÏĨ

0.14

Activations Density 0.012%

instances of assignment operations in code

No Comments

No Known Activations