INDEX

Explanations

concepts related to processes and workflows 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uder

-0.14

éĽª

-0.14

 onBind

-0.14

 sprav

-0.14

uv

-0.13

äºŃ

-0.13

UNCT

-0.13

erras

-0.13

CEE

-0.13

è¨

-0.13

POSITIVE LOGITS

 steps

0.25

 process

0.24

è¿ĩç¨ĭ

0.21

 procedure

0.20

process

0.20

steps

0.20

 Steps

0.19

_steps

0.19

 step

0.18

 proceso

0.18

Activations Density 0.336%

concepts related to processes and workflows in various contexts

No Comments

No Known Activations