INDEX

Explanations

words related to participation and participatory concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

inged

-0.18

halt

-0.17

ingers

-0.16

ings

-0.15

hiba

-0.15

liÅ¾

-0.15

.yahoo

-0.14

inger

-0.14

INGER

-0.14

zeÅĪ

-0.14

POSITIVE LOGITS

ip

0.32

ipation

0.28

ip

0.27

IP

0.27

Ip

0.26

ipe

0.24

ipa

0.24

ipp

0.24

Ip

0.24

-ip

0.23

Activations Density 0.007%

words related to participation and participatory concepts

No Comments

No Known Activations