INDEX

Explanations

phrases related to ratings and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

utor

-0.16

ast

-0.14

psilon

-0.14

-0.13

idel

-0.13

ilities

-0.13

uses

-0.13

orious

-0.13

 Yesterday

-0.13

ÙħÛĮ

-0.13

POSITIVE LOGITS

 sheer

0.18

irsch

0.17

arten

0.16

ActionCreators

0.15

PÅĻed

0.15

ynchronize

0.14

Falsy

0.14

anco

0.14

Knife

0.14

.sponge

0.14

Activations Density 0.105%

phrases related to ratings and evaluations

No Comments

No Known Activations