INDEX

Explanations

references to reputation and public perception

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

 TMPro

-0.16

umer

-0.15

ê·¹

-0.14

anton

-0.14

 Wonderland

-0.14

 SPDX

-0.13

nels

-0.13

CodeGen

-0.13

.cf

-0.13

enson

-0.13

POSITIVE LOGITS

 status

0.38

 popularity

0.37

 fame

0.36

 cach

0.35

 recognition

0.34

 renown

0.34

 standing

0.34

 stature

0.33

 reputation

0.32

 cache

0.31

Activations Density 0.387%

references to reputation and public perception

No Comments

No Known Activations