INDEX

Explanations

academic affiliations and credentials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 voks

-0.17

_UNSUPPORTED

-0.16

dech

-0.16

 neighb

-0.15

 hvad

-0.15

 Erotische

-0.15

Ã¼c

-0.14

ì»¤ìĬ¤

-0.14

 prostitut

-0.14

 eskort

-0.14

POSITIVE LOGITS

 Norwegian

0.43

 Oslo

0.42

 Norway

0.40

Nor

0.36

 Bergen

0.32

nor

0.31

Ã¸

0.31

NOR

0.30

Nor

0.28

.no

0.28

Activations Density 0.082%

academic affiliations and credentials

No Comments

No Known Activations