INDEX

Explanations

references to demos or trial versions of products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ka

-0.16

iqueta

-0.14

def

-0.14

 next

-0.14

erland

-0.13

inia

-0.13

Ð¾Ð²ÐµÑĢ

-0.13

aina

-0.13

ajs

-0.13

 minus

-0.13

POSITIVE LOGITS

strate

0.15

isc

0.15

æĸĻ

0.15

0.14

ë³

0.14

êµ°

0.14

stration

0.14

DRV

0.14

kinson

0.14

insky

0.14

Activations Density 0.008%

references to demos or trial versions of products

No Comments

No Known Activations