INDEX

Explanations

references to a specific person, likely related to the field of science or sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

gere

-0.19

elig

-0.17

ews

-0.17

akens

-0.16

eds

-0.15

osy

-0.15

ness

-0.15

 bang

-0.15

attering

-0.15

ed

-0.14

POSITIVE LOGITS

iday

0.19

ero

0.18

éģĵ

0.18

eri

0.17

ERO

0.17

ucci

0.16

BYTES

0.16

aro

0.16

ario

0.15

placer

0.15

Activations Density 0.003%

references to a specific person, likely related to the field of science or sports

No Comments

No Known Activations