INDEX

Explanations

references to the name "Saint" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

nea

-0.18

IGHL

-0.16

rites

-0.15

tainment

-0.15

ÑĢÑĸÐ²

-0.15

aset

-0.14

IGHLIGHT

-0.14

ubl

-0.14

olls

-0.14

ç°

-0.14

POSITIVE LOGITS

 Petersburg

0.23

liness

0.20

ly

0.20

hood

0.18

ed

0.18

0.17

 Louis

0.17

-ÐŁÐµÑĤÐµÑĢÐ±

0.17

0.16

 Michaels

0.16

Activations Density 0.020%

references to the name "Saint" and its variations

No Comments

No Known Activations