INDEX

Explanations

numerical citations or references to legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lut

-0.17

upo

-0.16

æĢģ

-0.15

-urlencoded

-0.15

fov

-0.15

tee

-0.15

ipers

-0.14

èĶ

-0.14

leted

-0.14

alom

-0.14

POSITIVE LOGITS

fahren

0.17

 drown

0.16

ogo

0.16

 anywhere

0.15

Ø§Ø±Ø©

0.15

 Wend

0.15

ensen

0.15

à¹ĥà¸Ī

0.14

wend

0.14

sap

0.14

Activations Density 0.014%

numerical citations or references to legal cases

No Comments

No Known Activations