INDEX

Explanations

interactions and discussions around conflict and negotiation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 orientation

-0.15

outu

-0.14

heck

-0.14

markup

-0.14

tent

-0.14

 Chern

-0.14

å©·

-0.14

ÐµÐºÑĥ

-0.14

mez

-0.14

lux

-0.14

POSITIVE LOGITS

angelo

0.16

INGTON

0.15

ington

0.15

aber

0.14

ilt

0.14

ison

0.14

asher

0.14

 plÃ¡

0.14

shake

0.14

 dialogs

0.14

Activations Density 0.337%

interactions and discussions around conflict and negotiation

No Comments

No Known Activations