INDEX

Explanations

geographical locations, specifically places in Canada and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aurus

-0.19

ÑĦÑĤ

-0.16

ion

-0.15

annel

-0.14

æ±ł

-0.14

JIT

-0.13

Ð»Ð¾Ð´

-0.13

 Curtain

-0.13

erd

-0.13

opic

-0.13

POSITIVE LOGITS

audi

0.17

åħ±åĴĮåĽ½

0.17

nesia

0.15

Å¡ti

0.15

iyas

0.15

 Minor

0.15

GBK

0.15

vur

0.15

ukes

0.14

Tier

0.14

Activations Density 0.099%

geographical locations, specifically places in Canada and their significance

No Comments

No Known Activations