INDEX

Explanations

technical references or components related to programming libraries and software development

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

ummies

-0.16

metics

-0.15

ssa

-0.15

Ð¾Ð·Ð²

-0.15

opa

-0.15

arry

-0.14

ensex

-0.14

RS

-0.14

-interest

-0.14

stab

-0.14

POSITIVE LOGITS

ange

0.15

 Discipline

0.15

Pont

0.15

 SHIFT

0.15

 Pont

0.15

 discipline

0.14

 prescribed

0.14

 diam

0.14

atz

0.14

Activations Density 0.008%

technical references or components related to programming libraries and software development

No Comments

No Known Activations