INDEX

Explanations

references to specific locations and types of land or housing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

otas

-0.17

oret

-0.16

aban

-0.15

 dear

-0.14

omp

-0.14

 Cant

-0.14

 pref

-0.14

 Cran

-0.14

 straight

-0.14

ifer

-0.14

POSITIVE LOGITS

<location

0.18

Ã¶h

0.16

unuz

0.15

 Pest

0.15

allery

0.15

 hObject

0.15

à¸²à¸Ł

0.14

incare

0.14

quette

0.14

ongoose

0.14

Activations Density 0.345%

references to specific locations and types of land or housing

No Comments

No Known Activations