INDEX

Explanations

references to object-oriented programming concepts or methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÙħØ§ÙĨÛĮ

-0.15

Pey

-0.15

Phy

-0.14

.fromFunction

-0.14

-fontawesome

-0.14

hawks

-0.14

nee

-0.14

reta

-0.14

anten

-0.13

archives

-0.13

POSITIVE LOGITS

osoph

0.16

/her

0.16

deaux

0.16

unsch

0.15

amma

0.15

enger

0.15

/us

0.15

é¾į

0.15

embre

0.14

Activations Density 0.042%

references to object-oriented programming concepts or methods

No Comments

No Known Activations