INDEX

Explanations

expressions of negotiation and compromise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

arih

-0.17

à¸¶

-0.14

Ú©ÙĦ

-0.14

oldur

-0.14

WindowSize

-0.14

Ã¤m

-0.14

enderit

-0.14

ibold

-0.14

hait

-0.14

errick

-0.14

POSITIVE LOGITS

 concessions

0.43

 concession

0.40

 compromise

0.40

 accommodation

0.37

 compromises

0.35

 accommodations

0.34

 accommod

0.33

 accommodate

0.33

 accom

0.32

 compromised

0.30

Activations Density 0.227%

expressions of negotiation and compromise

No Comments

No Known Activations