INDEX

Explanations

references to illegal activities or law enforcement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

/Foundation

-0.20

 sÃ³c

-0.16

.Mask

-0.16

oba

-0.15

erras

-0.15

 Ramp

-0.15

_native

-0.15

odb

-0.15

.epam

-0.15

/native

-0.14

POSITIVE LOGITS

 crossing

0.26

 migration

0.23

 immigration

0.22

 crossings

0.22

 Crossing

0.21

 migrants

0.20

 Migration

0.20

 border

0.20

 boat

0.19

 Immigration

0.18

Activations Density 0.059%

references to illegal activities or law enforcement

No Comments

No Known Activations