INDEX

Explanations

names and titles related to legal or judicial contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ypi

-0.16

ãģĿ

-0.14

ÏĢÎµÎ¹

-0.14

abox

-0.14

ago

-0.14

arry

-0.14

aths

-0.13

ÑĥÑģÑĤÐ°

-0.13

çŃĳ

-0.13

SOURCE

-0.13

POSITIVE LOGITS

et

0.24

 kiá»ĩn

0.20

dba

0.19

_et

0.18

0.17

 consolidated

0.17

 substituted

0.17

ex

0.17

db

0.16

 praying

0.16

Activations Density 0.112%

names and titles related to legal or judicial contexts

No Comments

No Known Activations