INDEX

Explanations

terms related to interest and financial fees

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

urd

-0.16

 Perr

-0.15

ients

-0.15

oppers

-0.15

umar

-0.14

ç§

-0.14

Validity

-0.14

ient

-0.13

 function

-0.13

Pie

-0.13

POSITIVE LOGITS

0.15

EAR

0.14

odate

0.14

@store

0.14

ansas

0.14

ystone

0.14

ologne

0.14

_Metadata

0.13

ovel

0.13

 simult

0.13

Activations Density 0.015%

terms related to interest and financial fees

No Comments

No Known Activations