INDEX

Explanations

programming terminology and data management concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

opus

-0.14

ongoose

-0.14

athi

-0.14

egan

-0.13

.native

-0.13

 Spit

-0.13

.opens

-0.13

ghan

-0.13

[...,

-0.13

ASI

-0.13

POSITIVE LOGITS

 Select

0.23

LIN

0.23

 select

0.23

Lin

0.21

lin

0.20

 Skip

0.20

 extension

0.20

lin

0.19

Select

0.18

 projection

0.18

Activations Density 0.023%

programming terminology and data management concepts

No Comments

No Known Activations