INDEX

Explanations

words indicating personal states or conditions related to identity and existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

omo

-0.16

:type

-0.15

mh

-0.15

endon

-0.14

ÙħØ§ÙĦ

-0.14

 Shower

-0.14

reactstrap

-0.14

é¡¶

-0.14

dyby

-0.14

POSITIVE LOGITS

alte

0.15

inÃ§

0.15

ãĥ³ãĥĩ

0.15

.Îķ

0.14

phans

0.14

ISE

0.14

ismet

0.14

/apps

0.13

tam

0.13

Activations Density 0.001%

words indicating personal states or conditions related to identity and existence

No Comments

No Known Activations