INDEX

Explanations

references to programming libraries and namespaces

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

-0.15

strom

-0.15

onto

-0.14

izont

-0.14

YD

-0.14

ruz

-0.14

engo

-0.14

ocop

-0.14

 addCriterion

-0.14

okin

-0.14

POSITIVE LOGITS

 Leban

0.17

erce

0.15

ìĹ´

0.15

erte

0.15

ewire

0.14

ptest

0.14

bery

0.14

rene

0.14

åºŃ

0.14

bral

0.14

Activations Density 0.001%

references to programming libraries and namespaces

No Comments

No Known Activations