INDEX

Explanations

references to the term "Mont" 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 @ 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

Ð¾ÑĢÐ¾Ð´

-0.16

omics

-0.15

ergus

-0.15

-0.14

keit

-0.14

DEX

-0.14

logen

-0.13

er

-0.13

ston

-0.13

omic

-0.13

POSITIVE LOGITS

gomery

0.28

enegro

0.26

essor

0.26

serrat

0.24

agne

0.23

pellier

0.22

gom

0.22

clair

0.22

aign

0.20

rose

0.20

Activations Density 0.012%

references to the term "Mont" in various contexts

No Comments

No Known Activations

references to the term "Mont" in various contexts

No Comments

No Known Activations