INDEX

Explanations

references to time, specifically days and weeks ago

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

ices

-0.15

nev

-0.15

uang

-0.15

.inline

-0.14

InSection

-0.14

anja

-0.14

ICES

-0.14

Alv

-0.13

connexion

-0.13

wig

-0.13

POSITIVE LOGITS

ody

0.16

ichern

0.15

0.14

ense

0.14

xFFF

0.14

aidu

0.14

arten

0.13

 Spicer

0.13

_GRE

0.13

/Object

0.13

Activations Density 0.010%

references to time, specifically days and weeks ago

No Comments

No Known Activations