INDEX

Explanations

mentions of the name "Gonzaga" 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 @ 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

imary

-0.17

hop

-0.16

Î®Î½

-0.15

OCK

-0.15

Hop

-0.15

 fisse

-0.15

antis

-0.14

rimon

-0.14

igm

-0.14

aigned

-0.14

POSITIVE LOGITS

alez

0.35

Ã¡lez

0.33

ales

0.25

alo

0.23

aga

0.19

lez

0.19

uez

0.18

orr

0.18

arez

0.18

lez

0.18

Activations Density 0.006%

mentions of the name "Gonzaga" and its variations

No Comments

No Known Activations

mentions of the name "Gonzaga" and its variations

No Comments

No Known Activations