INDEX

Explanations

references to political events and government responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 primes

-0.14

izi

-0.14

anto

-0.14

endon

-0.14

antine

-0.14

 scre

-0.14

NOI

-0.13

 Euler

-0.13

Ð¾Ð»Ð¾Ð²

-0.13

POSITIVE LOGITS

CM

0.31

 Chief

0.28

CM

0.25

Chief

0.25

ML

0.24

cm

0.24

ML

0.23

 chief

0.22

 Assembly

0.22

MLA

0.22

Activations Density 0.040%

references to political events and government responses

No Comments

No Known Activations