INDEX

Explanations

references to time, specifically indicating events or actions that occurred recently

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 ancient

-0.15

chal

-0.15

omet

-0.14

 overnight

-0.14

ric

-0.14

iram

-0.14

/engine

-0.14

 older

-0.14

old

-0.14

ic

-0.14

POSITIVE LOGITS

-than

0.25

_than

0.23

-stage

0.22

zeitig

0.20

çīĪæľ¬

0.20

most

0.20

/current

0.20

 than

0.20

 stages

0.18

anging

0.18

Activations Density 0.015%

references to time, specifically indicating events or actions that occurred recently

No Comments

No Known Activations