INDEX

Explanations

references to death and loss in a historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

imar

-0.17

è°

-0.15

aque

-0.15

é§Ĳ

-0.15

.metric

-0.15

 Earlier

-0.14

Ð¼ÐµÑĩ

-0.14

ĥģ

-0.14

Earlier

-0.14

 Feinstein

-0.14

POSITIVE LOGITS

ç«ľ

0.17

 Kart

0.14

favor

0.14

Hud

0.14

SOP

0.14

.enter

0.14

stroy

0.14

&S

0.14

 cursed

0.14

Neb

0.14

Activations Density 0.052%

references to death and loss in a historical context

No Comments

No Known Activations