INDEX

Explanations

software-related terms and properties pertaining to data structures and their configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

outh

-0.15

logg

-0.15

ois

-0.14

imp

-0.14

ale

-0.14

 fork

-0.13

aos

-0.13

POSITIVE LOGITS

ancies

0.15

emean

0.15

Î»Î»Î¹

0.15

ANCES

0.15

urator

0.14

isses

0.14

insky

0.14

mitter

0.14

rop

0.14

é£¯

0.14

Activations Density 0.072%

software-related terms and properties pertaining to data structures and their configurations

No Comments

No Known Activations