INDEX

Explanations

references to prominent individuals and their actions or statuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 ç©

-0.17

ekler

-0.15

emey

-0.14

ALA

-0.14

Ã¼cken

-0.14

 Bilg

-0.13

vida

-0.13

elman

-0.13

 altÄ±na

-0.13

ivol

-0.13

POSITIVE LOGITS

 Perez

0.15

 absorbing

0.15

achel

0.14

ibs

0.14

åĲ¸

0.14

ics

0.14

bai

0.14

ues

0.14

Activations Density 0.166%

references to prominent individuals and their actions or statuses

No Comments

No Known Activations