INDEX

Explanations

references to specific locations and real estate descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

aub

-0.18

enville

-0.16

 Kingston

-0.16

jay

-0.16

deaux

-0.15

ingham

-0.15

çĶĺ

-0.15

Yad

-0.15

serrat

-0.15

ubern

-0.15

POSITIVE LOGITS

 Venice

0.34

Ven

0.33

Ven

0.31

 Venez

0.26

 venez

0.23

ven

0.23

 Laguna

0.18

VEN

0.18

 mainland

0.17

lag

0.16

Activations Density 0.037%

references to specific locations and real estate descriptions

No Comments

No Known Activations