INDEX

Explanations

general rules and principles, particularly those related to decision-making and productivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

onet

-0.14

atos

-0.14

 Ãĸn

-0.14

EMU

-0.14

ibur

-0.13

Quest

-0.13

 Lester

-0.13

.fe

-0.13

çĮ®

-0.12

å¾Ħ

-0.12

POSITIVE LOGITS

 rule

0.52

 principle

0.44

 Rule

0.44

rule

0.43

 rules

0.43

 principles

0.42

Rule

0.40

 Principle

0.40

-rule

0.40

rules

0.38

Activations Density 0.287%

general rules and principles, particularly those related to decision-making and productivity

No Comments

No Known Activations