INDEX

Explanations

terms related to processing and refining in various contexts, particularly in science and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

inski

-0.15

Dag

-0.14

ModelState

-0.14

tur

-0.14

iper

-0.14

ever

-0.14

uela

-0.13

gren

-0.13

 Scalar

-0.13

zik

-0.13

POSITIVE LOGITS

acic

0.16

sville

0.15

erie

0.15

ãģĭãģĳ

0.15

elay

0.15

 Corm

0.15

STATIC

0.14

ityEngine

0.14

acid

0.14

FRING

0.14

Activations Density 0.401%

terms related to processing and refining in various contexts, particularly in science and technology

No Comments

No Known Activations