INDEX

Explanations

references to locations or streets, particularly those starting with "St."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

erve

-0.16

ORE

-0.15

cond

-0.15

ustum

-0.15

minster

-0.15

lyph

-0.15

 Henderson

-0.15

 Pend

-0.14

conte

-0.14

POSITIVE LOGITS

 Clair

0.23

ewart

0.22

-On

0.22

others

0.21

oj

0.20

.Cl

0.19

enger

0.19

olare

0.18

ahl

0.18

odd

0.18

Activations Density 0.015%

references to locations or streets, particularly those starting with "St."

No Comments

No Known Activations