INDEX

Explanations

financial ratings and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

undler

-0.16

ceptar

-0.16

 nÄĥ

-0.16

nev

-0.15

omm

-0.15

reff

-0.14

upos

-0.14

ulary

-0.14

undai

-0.13

 Cornel

-0.13

POSITIVE LOGITS

PATH

0.18

idth

0.15

 PATH

0.14

uncture

0.14

apis

0.14

roupe

0.14

 rating

0.13

ãĤ´ãĥª

0.13

sembler

0.13

aml

0.13

Activations Density 0.002%

financial ratings and related terms

No Comments

No Known Activations