INDEX

Explanations

references to a specific location or place, particularly related to the term "Prairie."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aida

-0.15

ron

-0.14

æĻ´

-0.14

Wid

-0.14

 shine

-0.14

 shadows

-0.13

 Naturally

-0.13

nett

-0.13

 reactions

-0.13

 adress

-0.13

POSITIVE LOGITS

chwitz

0.20

osg

0.18

ovÃŃ

0.17

onium

0.16

ois

0.15

arious

0.15

uw

0.15

agens

0.15

iger

0.14

lav

0.14

Activations Density 0.005%

references to a specific location or place, particularly related to the term "Prairie."

No Comments

No Known Activations