INDEX

Explanations

features and functionalities of software and tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

imon

-0.13

etik

-0.13

.habbo

-0.13

elden

-0.13

hu

-0.12

lund

-0.12

åĴ²

-0.12

 orders

-0.12

orders

-0.12

olla

-0.12

POSITIVE LOGITS

 features

0.81

features

0.68

 Features

0.67

Features

0.61

 feature

0.58

 FEATURES

0.58

_features

0.56

/features

0.50

.features

0.50

feature

0.49

Activations Density 0.311%

features and functionalities of software and tools

No Comments

No Known Activations