INDEX

Explanations

phrases indicating capability or potential actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

aldo

-0.16

AVA

-0.14

elho

-0.14

adele

-0.14

/comment

-0.14

 Tele

-0.14

 ÑĢÐµÐ²

-0.13

noÅĽci

-0.13

arching

-0.13

batim

-0.13

POSITIVE LOGITS

-Ass

0.16

ima

0.15

 Mattis

0.14

panse

0.14

aise

0.14

ojis

0.14

 saja

0.14

URNS

0.14

azen

0.14

nil

0.13

Activations Density 0.152%

phrases indicating capability or potential actions

No Comments

No Known Activations