INDEX

Explanations

references to time, particularly in relation to past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uther

-0.22

ondo

-0.15

ham

-0.15

adol

-0.14

wich

-0.14

akov

-0.14

romo

-0.14

han

-0.14

GetMethod

-0.14

zan

-0.14

POSITIVE LOGITS

rophy

0.15

emon

0.15

evin

0.14

SSI

0.14

áº£nh

0.14

sss

0.14

esium

0.14

aron

0.14

ssel

0.14

è

0.13

Activations Density 0.005%

references to time, particularly in relation to past events

No Comments

No Known Activations