INDEX

Explanations

details about components and their relationships in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Éµ

-0.17

luet

-0.16

isos

-0.15

ãĥªãĥ¼ãĤº

-0.15

opensource

-0.14

/twitter

-0.14

emd

-0.14

xB

-0.14

.fun

-0.14

Examples

-0.14

POSITIVE LOGITS

 components

0.27

-components

0.23

components

0.23

 elements

0.22

 Components

0.19

 ÐºÐ¾Ð¼Ð¿Ð¾Ð½

0.19

(components

0.19

 parts

0.18

 component

0.18

 ingredients

0.18

Activations Density 0.286%

details about components and their relationships in various contexts

No Comments

No Known Activations