INDEX

Explanations

conditional phrases related to agreement or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

mrt

-0.17

ambi

-0.15

upro

-0.14

lights

-0.14

amation

-0.14

 Rosenstein

-0.14

undi

-0.13

fir

-0.13

rong

-0.13

POSITIVE LOGITS

elmet

0.19

enas

0.17

æĪĲäºº

0.16

attern

0.15

enger

0.15

 æ´

0.15

sembly

0.15

efined

0.14

 floated

0.14

Activations Density 0.177%

conditional phrases related to agreement or understanding

No Comments

No Known Activations