INDEX

Explanations

phrases related to scrutiny and criticism of public figures, particularly in journalism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 eventually

-0.22

 finally

-0.20

 final

-0.20

 eventual

-0.17

 already

-0.16

 devel

-0.15

 Eventually

-0.15

 ultimately

-0.14

 mixed

-0.14

 parts

-0.14

POSITIVE LOGITS

simple

0.26

 simplest

0.25

 simples

0.25

 simple

0.25

-simple

0.24

 einfach

0.23

 simply

0.21

Simple

0.20

ç®Ģåįķ

0.20

 Simple

0.20

Activations Density 0.048%

phrases related to scrutiny and criticism of public figures, particularly in journalism

No Comments

No Known Activations